fix(reference): route exit codes through setCliExitVerdict; use withEnv in e2e test

CI red on two guards:
- test/cli-exit-verdict-pin.test.ts: raw process.exitCode writes in
  src/commands/reference.ts -> replaced with setCliExitVerdict.
- check:test-isolation R1: direct process.env.GBRAIN_SOURCE mutation in
  test/reference-flag.test.ts -> wrapped the two runReference calls in
  withEnv({ GBRAIN_SOURCE: undefined }).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

llms-full.txt

@@ -1411,8 +1411,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
 | "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
 | Save or load reports | `skills/reports/SKILL.md` |
 | "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
-| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
-| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
+| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
 | "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
 | "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
 | "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
@@ -1430,7 +1429,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
 | "Set up GBrain", first boot | `skills/setup/SKILL.md` |
 | "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
 | "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
-| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
 | Brain health check, maintenance run | `skills/maintain/SKILL.md` |
 | "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
 | "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |

openclaw.plugin.json

@@ -39,8 +39,8 @@
     "skills/briefing",
     "skills/citation-fixer",
     "skills/concept-synthesis",
-    "skills/cron-scheduler",
     "skills/cross-modal-review",
+    "skills/cron-scheduler",
     "skills/daily-task-manager",
     "skills/daily-task-prep",
     "skills/data-research",
@@ -54,11 +54,10 @@
     "skills/media-ingest",
     "skills/meeting-ingestion",
     "skills/minion-orchestrator",
-    "skills/obsidian-gbrain-safe-index",
     "skills/perplexity-research",
     "skills/query",
-    "skills/repo-architecture",
     "skills/reports",
+    "skills/repo-architecture",
     "skills/signal-detector",
     "skills/skill-creator",
     "skills/skillify",

skills/RESOLVER.md

@@ -60,8 +60,7 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
 | "get more out of gbrain", "is my brain set up right", "weekly brain checkup", "advise me on my brain", "gbrain advisor" | `skills/gbrain-advisor/SKILL.md` |
 | Save or load reports | `skills/reports/SKILL.md` |
 | "Create a skill", "improve this skill" | `skills/skill-creator/SKILL.md` |
-| "save this learning to the vault", "capture this skill in Obsidian", "record this workflow in my notes", "put this setup change in the vault" | `skills/skill-vault-capture-policy/SKILL.md` |
-| "Skillify this", "is this a skill?", "make this proper", "add tests and evals for this" | `skills/skillify/SKILL.md` |
+| "Skillify this", "is this a skill?", "make this proper" | `skills/skillify/SKILL.md` |
 | "Compress my resolver", "AGENTS.md too large", "RESOLVER.md too big", "functional area dispatcher", "shrink routing table" | `skills/functional-area-resolver/SKILL.md` |
 | "Is gbrain healthy?", morning health check, skillpack-check | `skills/skillpack-check/SKILL.md` |
 | "harvest this skill into gbrain", "publish this skill to gbrain", "lift this skill upstream", "share this skill with other gbrain clients", "promote my skill to gbrain" | `skills/skillpack-harvest/SKILL.md` |
@@ -79,7 +78,6 @@ This is the dispatcher. Skills are the implementation. **Read the skill file bef
 | "Set up GBrain", first boot | `skills/setup/SKILL.md` |
 | "Now what?", "fill my brain", "cold start", "bootstrap", "import my data", "what should I import first" | `skills/cold-start/SKILL.md` |
 | "Migrate from Obsidian/Notion/Logseq" | `skills/migrate/SKILL.md` |
-| "Connect Obsidian to gbrain", "import my vault to gbrain", "sync vault and gbrain", "embed gbrain after vault update", "is gbrain synced with my vault" | `skills/obsidian-gbrain-safe-index/SKILL.md` |
 | Brain health check, maintenance run | `skills/maintain/SKILL.md` |
 | "Extract links", "build link graph", "populate timeline" | `skills/maintain/SKILL.md` (extraction sections) |
 | "Run dream", "process today's session", "synthesize my conversations", "consolidate yesterday's conversations", "what patterns did you see", "did the dream cycle run" | `skills/maintain/SKILL.md` (dream cycle section) |

skills/article-enrichment/SKILL.md

@@ -85,6 +85,10 @@ gbrain get media/articles/<slug>
 
 # 5. Cross-link entities
 #    For every person/company mentioned, add a timeline back-link.
+#    Mark NEW pages minted for article subjects the reader only reads ABOUT
+#    (not personal contacts) as reference: `gbrain reference <slug>`
+#    (or reference: true in frontmatter). Exempts them from coverage nudges;
+#    they stay searchable. Default for real contacts: do NOT set it.
 ```
 
 ## Quality bar

skills/book-mirror/SKILL.md

@@ -273,6 +273,13 @@ Cross-link entities mentioned in the analysis:
 - For every person the right column references with a brain page, add a
   back-link from `people/<slug>` to the new `media/books/<slug>-personalized`
   page (per `conventions/quality.md` Iron Law).
+- **Mark book figures as reference entities.** Any NEW person/company page you
+  mint for a figure from the book (an author, a historical figure, a company
+  the book discusses) — someone the reader reads ABOUT but doesn't personally
+  interact with — should be flagged: `gbrain reference <slug>` (or
+  `reference: true` in frontmatter). They stay fully searchable/linkable but
+  are exempt from coverage nudges (timeline/links). Skip this for anyone the
+  reader actually knows. Default for normal contacts: do NOT set it.
 
 ## Quality bar (the bar)
 

skills/conventions/reference-entities.md

@@ -0,0 +1,62 @@
+# Convention: Reference entities (canon figures)
+
+Some person/company pages are people/orgs the user **reads about** but does not
+personally interact with — a book's author, a historical figure, a company an
+article discusses (Andy Grove, Kleiner Perkins, Intel…). They are real
+knowledge, worth a page, but they have **no dated history in the user's own
+life**, so the entity coverage metrics (`timeline_coverage`,
+`entity_link_coverage`) flag them as permanently incomplete with no honest fix.
+
+The `reference: true` frontmatter flag resolves this.
+
+## What it does
+
+- A page with `reference: true` is **exempt from the entity coverage metrics
+  only** (`timeline_coverage`, `entity_link_coverage`, and their onboard
+  nudges).
+- It keeps its real `type` (`person` / `company`), so it stays **fully
+  searchable, enrichable, linkable, and edge-resolvable**. NOTHING about
+  retrieval changes — this is the whole reason it's a flag, not a new `type`.
+- It is **opt-in**. Absent / `false` / anything-but-`true` = a normal entity
+  that DOES count toward coverage. **This is the default — do not set it on real
+  contacts.**
+
+## When to set it
+
+Set `reference: true` when the entity is a figure/org the user reads ABOUT, not
+someone they deal with:
+
+- authors and figures discussed in a book (book-mirror) or article
+  (article-enrichment)
+- historical / canon figures imported as reference knowledge
+- companies named only as examples in source material
+
+Do NOT set it for people the user actually meets, emails, or works with — those
+are normal entities whose missing timeline/links is a real, actionable gap.
+
+## How to set it
+
+```bash
+gbrain reference <slug>            # mark as reference
+gbrain reference <slug> --unset    # back to a normal entity
+```
+
+The command writes the flag to BOTH the markdown frontmatter (durable; survives
+re-ingest / engine rebuild — markdown is the source of truth) AND the engine
+JSONB (so coverage reflects it immediately, no re-sync). It's idempotent. You
+can also hand-edit frontmatter (`reference: true`) and re-ingest.
+
+## Why a flag, not a type
+
+A new `type: reference-person` would drop the page out of every
+`type IN ('person','company')` filter — search, enrichment, whoknows, link
+inference — so you'd lose the figure everywhere, not just the metric. The flag
+narrows the change to exactly the coverage denominators and nothing else.
+
+## Implementation
+
+`src/core/reference-flag.ts` — `referenceExclusionSql(alias?)` is the single
+source of truth for the predicate `(frontmatter->>'reference') IS DISTINCT FROM
+'true'`, ANDed into both numerator and denominator at every coverage site
+(getHealth in both engines, onboard/checks.ts, init-nudge.ts). Backed by the GIN
+index on `pages.frontmatter`.

skills/enrich/SKILL.md

@@ -268,6 +268,18 @@ Active items, pending decisions, things to track.
 - **YYYY-MM-DD** | Event description [Source: ...]
 ```
 
+### Reference entities (canon figures)
+
+If the entity is someone/something the user reads ABOUT but does not personally
+interact with — a book author, a historical figure, a company discussed in an
+article — mark the page as reference: `gbrain reference <slug>` (or
+`reference: true` in frontmatter). Reference pages keep their `person`/`company`
+type and stay fully searchable, enrichable, and linkable; they are only exempt
+from the entity coverage nudges (timeline/links) that don't apply to figures
+with no dated history in the user's own life. **Default: do NOT set it** — real
+people and companies the user deals with are normal entities. Full convention:
+`conventions/reference-entities.md`.
+
 ### Step 7: Cross-reference
 
 - Update company pages from person enrichment (and vice versa)

skills/maintain/SKILL.md

@@ -270,6 +270,11 @@ Populate them periodically or after major imports:
 - `gbrain stats` — verify `link_count > 0` and `timeline_entry_count > 0` after extraction.
 - `gbrain health` — review `link_coverage` and `timeline_coverage` percentages
   on entity pages (person/company). Below 50% means more extraction is needed.
+  Note: pages flagged `reference: true` (canon/reference figures the user only
+  reads about) are EXEMPT from these two metrics — if coverage looks stuck
+  because of book/article-imported figures with no real history, mark them with
+  `gbrain reference <slug>` rather than chasing the percentage. See
+  `conventions/reference-entities.md`.
 
 Available link types (use with `gbrain graph-query --type`):
 `attended`, `works_at`, `invested_in`, `founded`, `advises`, `mentions`, `source`.

skills/manifest.json

@@ -2,7 +2,7 @@
   "name": "gbrain",
   "version": "0.32.3.0",
   "conformance_version": "1.0.0",
-  "description": "Personal knowledge brain with hybrid RAG search — GStack mod for agent platforms",
+  "description": "Personal knowledge brain with hybrid RAG search \u2014 GStack mod for agent platforms",
   "skills": [
     {
       "name": "ingest",
@@ -34,11 +34,6 @@
       "path": "migrate/SKILL.md",
       "description": "Universal migration from Obsidian, Notion, Logseq, markdown, CSV, JSON, Roam"
     },
-    {
-      "name": "obsidian-gbrain-safe-index",
-      "path": "obsidian-gbrain-safe-index/SKILL.md",
-      "description": "Connect and sync an Obsidian-style Markdown vault with gbrain using a cost-controlled import-first workflow, explicit embedding gates, and durable skill/workflow capture."
-    },
     {
       "name": "setup",
       "path": "setup/SKILL.md",
@@ -268,11 +263,6 @@
       "name": "skill-optimizer",
       "path": "skill-optimizer/SKILL.md",
       "description": "Self-evolving skill optimization via gbrain skillopt — SkillOpt-paper-grounded text-space optimizer with validation gating (median-of-3 + epsilon=0.05), bundled-skill safety, bootstrap review sentinel, per-skill DB lock, and atomic versioned writes."
-    },
-    {
-      "name": "skill-vault-capture-policy",
-      "path": "skill-vault-capture-policy/SKILL.md",
-      "description": "Capture durable operational learnings, new agent skills, and environment/setup changes into the Obsidian vault instead of transient chat memory."
     }
   ],
   "dependencies": {

skills/obsidian-gbrain-safe-index/SKILL.md

@@ -1,137 +0,0 @@
----
-name: obsidian-gbrain-safe-index
-version: 1.0.0
-description: |
-  Connect, maintain, and sync an Obsidian-style Markdown vault with gbrain while preserving a cost-controlled workflow: the vault remains the source of truth, gbrain is the searchable/embedded index, durable skills/workflows are captured into the vault, and paid embedding runs only after explicit approval.
-triggers:
-  - "connect Obsidian to gbrain"
-  - "import my vault to gbrain"
-  - "sync vault and gbrain"
-  - "capture this skill in my vault"
-  - "embed gbrain after vault update"
-  - "is gbrain synced with my vault"
-tools:
-  - terminal
-  - read_file
-  - search_files
-  - write_file
-  - patch
-mutating: true
----
-
-# Obsidian → gbrain Safe Index and Capture
-
-## Contract
-
-This skill guarantees:
-
-- Treats the user's Obsidian-style Markdown vault as the source of truth before gbrain indexing.
-- Keeps gbrain in conservative mode unless the user explicitly approves a more expensive mode.
-- Imports vault changes with `--no-embed` first, then embeds only after explicit approval for the specific paid action.
-- Captures durable new skills, workflows, and environment learnings into the vault instead of leaving them only in chat memory.
-- Verifies every sync with concrete `gbrain stats`, search mode, and, when embeddings run, exact embedded chunk counts.
-
-## Phases
-
-1. **Resolve the vault path.**
-   - Prefer an existing environment variable such as `OBSIDIAN_VAULT_PATH` or `WIKI_PATH`.
-   - If no path is configured, search likely note directories and ask the user before writing.
-   - Verify the directory exists and contains markdown files or an `.obsidian` directory.
-
-2. **Read vault operating rules before writing.**
-   - If the vault has `SCHEMA.md`, `index.md`, `log.md`, `AGENTS.md`, or similar operating files, read them before ingest/query/major edit.
-   - Respect immutable source folders such as `raw/` when the vault declares them.
-   - Use the vault's native link convention, usually Obsidian `[[wikilinks]]`, for durable relationships.
-
-3. **MECE/capture decision.**
-   - If new knowledge belongs on an existing page, update that page.
-   - If it is a distinct recurring workflow or operational policy, create a small meta or concept page following the vault schema.
-   - Update the vault index/catalog for every new page when the vault maintains one.
-   - Append a log entry for meaningful vault updates when the vault maintains a log.
-
-4. **Safe gbrain import path.**
-   - Pre-check source directory; do not import a nonexistent path.
-   - Run `gbrain config set search.mode conservative` before/after risky reinit steps.
-   - Run `gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed`.
-   - Run `gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"` when wikilinks changed materially.
-
-5. **Paid embedding gate.**
-   - Do not run `gbrain embed --stale` unless the user explicitly asks or a prior instruction clearly approved this exact paid action.
-   - Before embedding, verify provider readiness with `gbrain providers test --model <provider:model>`.
-   - Confirm the configured embedding dimensions match the local schema.
-   - After embedding, verify `gbrain stats` and record exact `Pages`, `Chunks`, `Embedded`, and `Links` counts.
-
-6. **Final verification and vault echo.**
-   - Run `gbrain stats` and `gbrain search modes`.
-   - If vault files changed, re-import with `--no-embed`; if embedding was approved, embed stale chunks afterward.
-   - Report what changed, what was free/local, what used API billing, and what remains pending.
-
-## Output Format
-
-Use a compact status table:
-
-| Item | Status |
-|---|---|
-| Vault path | `/path` |
-| Vault updated | yes/no + files |
-| gbrain mode | conservative/balanced/tokenmax |
-| Import | `--no-embed` completed / skipped / failed |
-| Pages/chunks | exact counts from `gbrain stats` |
-| Embeddings | exact count; note whether this run used API billing |
-| Links | exact count |
-| Background jobs | none / list exact jobs |
-
-Then include:
-
-- **Safe next step:** free/local action.
-- **Paid next step:** embedding/LLM action, if any, with explicit approval requirement.
-
-## Anti-Patterns
-
-- Creating a duplicate skill/page when an existing Obsidian, gbrain, or vault-ingest skill already covers the workflow.
-- Running `gbrain embed --stale`, `gbrain dream`, `gbrain autopilot --install`, `gbrain onboard --auto`, or `tokenmax` without explicit cost approval.
-- Importing a nonexistent or wrong directory and treating a zero-page import as success.
-- Forgetting to update the vault index/catalog and log after creating or materially updating vault pages.
-- Recording API keys, tokens, or raw secrets in the vault or final response.
-
-## Tools Used
-
-- `read_file` — read vault schema/index/log and target notes.
-- `search_files` — find existing vault pages and avoid duplicates.
-- `write_file` / `patch` — create or update vault pages.
-- `terminal` — run `gbrain`, `git`, and environment checks with secret values redacted.
-
-## Safe Commands
-
-```bash
-export PATH="$HOME/.bun/bin:$PATH"
-gbrain config set search.mode conservative
-gbrain import "$OBSIDIAN_VAULT_PATH" --no-embed
-gbrain extract links --source fs --dir "$OBSIDIAN_VAULT_PATH"
-gbrain stats
-gbrain search modes
-```
-
-## Paid / Approval-Gated Commands
-
-```bash
-gbrain providers test --model <provider:model>
-gbrain embed --stale
-gbrain dream
-gbrain autopilot --install
-gbrain onboard --auto --max-usd 5
-gbrain config set search.mode tokenmax
-```
-
-## Verification Checklist
-
-- [ ] Vault path exists and is the intended source.
-- [ ] Vault operating files were read before edits when present.
-- [ ] Existing pages/skills were searched to avoid duplicates.
-- [ ] New/updated vault pages follow the vault schema and link convention.
-- [ ] Vault index/catalog updated for new pages when present.
-- [ ] Vault log appended for meaningful actions when present.
-- [ ] `gbrain import ... --no-embed` completed.
-- [ ] `gbrain stats` recorded pages/chunks/embeddings/links.
-- [ ] `gbrain search modes` confirms conservative mode unless a different mode was explicitly approved.
-- [ ] No paid/background commands ran without approval.

skills/obsidian-gbrain-safe-index/routing-eval.jsonl

@@ -1,11 +0,0 @@
-// Routing eval fixtures for skills/obsidian-gbrain-safe-index.
-// Positive cases: intents embed a trigger phrase in natural surrounding context
-// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
-{"intent": "help me connect Obsidian to gbrain for my notes", "expected_skill": "obsidian-gbrain-safe-index"}
-{"intent": "import my vault to gbrain but skip embeddings for now", "expected_skill": "obsidian-gbrain-safe-index"}
-{"intent": "please sync vault and gbrain after I edit notes", "expected_skill": "obsidian-gbrain-safe-index"}
-{"intent": "run embed gbrain after vault update tonight", "expected_skill": "obsidian-gbrain-safe-index"}
-{"intent": "hey is gbrain synced with my vault right now", "expected_skill": "obsidian-gbrain-safe-index"}
-// Negative cases: related but owned by other skills. Assert NO route to this skill.
-{"intent": "migrate my notes from Notion to gbrain", "expected_skill": null}
-{"intent": "what is on my calendar tomorrow", "expected_skill": null}

skills/skill-vault-capture-policy/SKILL.md

@@ -1,100 +0,0 @@
----
-name: skill-vault-capture-policy
-version: 1.0.0
-description: |
-  Use when the user wants a durable operational learning, new agent skill, or
-  important environment/setup change to be captured into the Obsidian vault
-  instead of left only in transient chat memory. Covers the capture rule,
-  preferred page patterns, and index/log update obligations.
-triggers:
-  - "save this learning to the vault"
-  - "capture this skill in Obsidian"
-  - "record this workflow in my notes"
-  - "put this setup change in the vault"
-  - "should we add this to the knowledge base"
-tools:
-  - read_file
-  - search_files
-  - write_file
-  - patch
-mutating: true
----
-
-# Skill Vault Capture Policy
-
-## Contract
-
-This skill guarantees:
-
-- Durable operational learnings, newly adopted skills, and important environment/setup changes are captured into the Obsidian vault rather than left only in chat memory.
-- An existing page is updated when the knowledge clearly belongs there; a new page is created only when the topic is distinct and likely to recur.
-- Every new vault page is added to `index.md`.
-- Every meaningful create/update appends a dated entry to `log.md`.
-- Small linked pages are preferred over one giant running note.
-
-## Phases
-
-1. **Classify the learning.**
-   - New gbrain operating rule, cost control, or embedding/provider change.
-   - New agent-fork / harness / coding-tool integration fact.
-   - New Obsidian vault workflow or structure decision.
-   - New recurring agent skill that changes how the agent should operate here.
-
-2. **Avoid duplicates.**
-   - Search the vault for an existing page that already owns the topic.
-   - If found, update it with a new section or dated note rather than creating a near-duplicate.
-
-3. **Create when distinct.**
-   - Place new pages under the vault schema: `_meta/` for operating notes, `concepts/` for workflows, `entities/` for tools/people.
-   - Use YAML frontmatter and at least two `[[wikilinks]]` unless it is a short seed page.
-
-4. **Update navigation.**
-   - Add the page to `index.md` under the correct type heading.
-   - Append a `## [YYYY-MM-DD] create|update | subject` entry to `log.md`.
-
-5. **Report the capture.**
-   - State which files changed and whether `index.md` / `log.md` were updated.
-
-## Output Format
-
-Use a short status block:
-
-| Item | Status |
-|---|---|
-| Learning classified | type |
-| Page created/updated | path |
-| index.md updated | yes/no |
-| log.md updated | yes/no |
-
-## Anti-Patterns
-
-- Leaving durable learnings only in chat memory.
-- Creating a near-duplicate page instead of updating the existing one.
-- Forgetting to update `index.md` and `log.md`.
-- Writing one giant running note instead of small linked pages.
-- Recording secrets, API keys, or raw credentials in the vault.
-
-## Tools Used
-
-- `read_file` — read `SCHEMA.md`, `index.md`, `log.md`, and target pages.
-- `search_files` — find existing pages to avoid duplicates.
-- `write_file` / `patch` — create or update vault pages and navigation.
-
-## Safe Commands
-
-```bash
-# inspect vault navigation before writing
-read SCHEMA.md index.md log.md
-# create or update a page, then refresh catalog/log
-# index.md: add [[page-slug]] under the matching type heading
-# log.md: append ## [YYYY-MM-DD] create|update | subject
-```
-
-## Verification Checklist
-
-- [ ] Vault schema/read files were checked before writing.
-- [ ] Existing pages were searched to avoid duplicates.
-- [ ] New/updated page has frontmatter and wikilinks.
-- [ ] `index.md` updated for new pages.
-- [ ] `log.md` appended for meaningful actions.
-- [ ] No secrets or raw credentials were written.

skills/skill-vault-capture-policy/routing-eval.jsonl

@@ -1,10 +0,0 @@
-// Routing eval fixtures for skills/skill-vault-capture-policy.
-// Positive cases: intents embed a trigger phrase in natural surrounding context
-// (never verbatim-identical to a trigger — the fixture linter rejects tautologies).
-{"intent": "please save this learning to the vault so we keep it", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["idea-ingest"]}
-{"intent": "we should capture this skill in Obsidian for reuse", "expected_skill": "skill-vault-capture-policy", "ambiguous_with": ["capture"]}
-{"intent": "can you record this workflow in my notes for next time", "expected_skill": "skill-vault-capture-policy"}
-{"intent": "put this setup change in the vault before we forget", "expected_skill": "skill-vault-capture-policy"}
-// Negative cases: related but owned by other skills or out of scope.
-{"intent": "connect my Obsidian vault to gbrain", "expected_skill": null}
-{"intent": "what is on my calendar tomorrow", "expected_skill": null}

src/cli.ts

@@ -54,7 +54,7 @@ export function bigintToStringReplacer(_key: string, value: unknown): unknown {
 }
 
 // CLI-only commands that bypass the operation layer
-export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
+export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'reference', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
 // CLI-only commands whose handlers print their own --help text. These are
 // excluded from the generic short-circuit so detailed per-command and
 // per-subcommand usage stays reachable.
@@ -1652,6 +1652,11 @@ async function handleCliOnly(command: string, args: string[]) {
         await runFiles(engine, args);
         break;
       }
+      case 'reference': {
+        const { runReference } = await import('./commands/reference.ts');
+        await runReference(engine, args);
+        break;
+      }
       case 'embed': {
         const { runEmbed } = await import('./commands/embed.ts');
         await runEmbed(engine, args);

src/commands/reference.ts

@@ -0,0 +1,130 @@
+// gbrain reference <slug> [--unset] [--brain <dir>] [--json]
+//
+// Mark (or unmark) a page as a reference-only entity. A reference page keeps its
+// real type (person/company) — fully searchable/enrichable/linkable — but is
+// exempt from the entity coverage metrics (timeline_coverage,
+// entity_link_coverage). See src/core/reference-flag.ts for the rationale.
+//
+// Durability: the flag is written to BOTH the markdown frontmatter (source of
+// truth; survives re-ingest / engine rebuild) AND the engine `pages.frontmatter`
+// JSONB (so the metric reflects it immediately, no re-sync needed).
+
+import { existsSync, readFileSync, writeFileSync } from 'node:fs';
+import { isAbsolute, join, resolve } from 'node:path';
+import { setCliExitVerdict } from '../core/cli-force-exit.ts';
+import type { BrainEngine } from '../core/engine.ts';
+import { REFERENCE_FRONTMATTER_KEY } from '../core/reference-flag.ts';
+import { resolveSourceId } from '../core/source-resolver.ts';
+
+/** Insert/replace/remove `reference: true` in a markdown frontmatter block.
+ *  Minimal-diff: only the one line changes; key order is otherwise preserved. */
+export function applyReferenceFrontmatter(content: string, on: boolean): string {
+  const keyLine = `${REFERENCE_FRONTMATTER_KEY}: true`;
+  const block = content.match(/^---\n([\s\S]*?)\n---/);
+
+  if (!block) {
+    // No frontmatter. Nothing to remove; if setting, prepend a block.
+    if (!on) return content;
+    return `---\n${keyLine}\n---\n\n${content}`;
+  }
+
+  let fm = block[1];
+  const hasKey = new RegExp(`^${REFERENCE_FRONTMATTER_KEY}:.*$`, 'm').test(fm);
+
+  if (on) {
+    fm = hasKey
+      ? fm.replace(new RegExp(`^${REFERENCE_FRONTMATTER_KEY}:.*$`, 'm'), keyLine)
+      : `${fm}\n${keyLine}`;
+  } else {
+    if (!hasKey) return content;
+    fm = fm.replace(new RegExp(`^${REFERENCE_FRONTMATTER_KEY}:.*$\\n?`, 'm'), '');
+  }
+
+  // Function replacement so YAML chars ($, & …) in fm aren't treated as
+  // replacement patterns.
+  return content.replace(/^---\n[\s\S]*?\n---/, () => `---\n${fm}\n---`);
+}
+
+function parseArgs(args: string[]): { slug?: string; unset: boolean; json: boolean; brain?: string; source?: string } {
+  let slug: string | undefined;
+  let unset = false;
+  let json = false;
+  let brain: string | undefined;
+  let source: string | undefined;
+  for (let i = 0; i < args.length; i++) {
+    const a = args[i];
+    if (a === '--unset') unset = true;
+    else if (a === '--json') json = true;
+    else if (a === '--brain' || a === '--dir') brain = args[++i];
+    else if (a === '--source') source = args[++i];
+    else if (!a.startsWith('--') && !slug) slug = a;
+  }
+  return { slug, unset, json, brain, source };
+}
+
+async function resolveBrainDir(engine: BrainEngine, explicit?: string): Promise<string | null> {
+  if (explicit) return resolve(explicit);
+  const configured = await engine.getConfig('sync.repo_path');
+  if (configured && existsSync(configured)) return resolve(configured);
+  return null;
+}
+
+export async function runReference(engine: BrainEngine, args: string[]): Promise<void> {
+  const { slug, unset, json, brain, source } = parseArgs(args);
+  if (!slug) {
+    console.error('Usage: gbrain reference <slug> [--unset] [--source <id>] [--brain <dir>] [--json]');
+    setCliExitVerdict(2);
+    return;
+  }
+
+  const brainDir = await resolveBrainDir(engine, brain);
+  if (!brainDir) {
+    console.error('reference: could not resolve brain dir. Pass --brain <dir> or set sync.repo_path.');
+    setCliExitVerdict(1);
+    return;
+  }
+
+  const rel = slug.endsWith('.md') ? slug : `${slug}.md`;
+  const filePath = isAbsolute(rel) ? rel : join(brainDir, rel);
+  if (!existsSync(filePath)) {
+    console.error(`reference: page not found on disk: ${filePath}`);
+    setCliExitVerdict(1);
+    return;
+  }
+
+  // 1) Durable: edit the markdown frontmatter.
+  const before = readFileSync(filePath, 'utf8');
+  const after = applyReferenceFrontmatter(before, !unset);
+  const fileChanged = after !== before;
+  if (fileChanged) writeFileSync(filePath, after, 'utf8');
+
+  // 2) Immediate: update the engine frontmatter JSONB so the metric reflects it
+  //    without waiting for a re-sync. Scoped to (source_id, slug) — slug is only
+  //    unique per source, so a bare-slug UPDATE would clobber same-named pages
+  //    in every other source. Resolve the source from the brain dir (tier-4
+  //    local_path match) unless --source / GBRAIN_SOURCE overrides.
+  const cleanSlug = slug.replace(/\.md$/, '');
+  const sourceId = await resolveSourceId(engine, source ?? null, brainDir);
+  if (unset) {
+    await engine.executeRaw(
+      `UPDATE pages SET frontmatter = frontmatter - '${REFERENCE_FRONTMATTER_KEY}' WHERE slug = $1 AND source_id = $2`,
+      [cleanSlug, sourceId],
+    );
+  } else {
+    await engine.executeRaw(
+      `UPDATE pages SET frontmatter = jsonb_set(COALESCE(frontmatter, '{}'::jsonb), '{${REFERENCE_FRONTMATTER_KEY}}', 'true'::jsonb) WHERE slug = $1 AND source_id = $2`,
+      [cleanSlug, sourceId],
+    );
+  }
+
+  const result = { slug: cleanSlug, source_id: sourceId, reference: !unset, file_changed: fileChanged, file: filePath };
+  if (json) {
+    console.log(JSON.stringify(result));
+  } else {
+    const verb = unset ? 'unmarked' : 'marked';
+    console.log(`${verb} ${cleanSlug} as reference=${!unset}${fileChanged ? '' : ' (frontmatter already current)'}`);
+    if (!unset) {
+      console.log('  → exempt from timeline_coverage / entity_link_coverage; still fully searchable & linkable.');
+    }
+  }
+}

src/core/onboard/checks.ts

@@ -18,6 +18,7 @@
 import type { BrainEngine } from '../engine.ts';
 import type { RemediationStep } from '../remediation-step.ts';
 import { makeRemediationStep } from '../remediation-step.ts';
+import { referenceExclusionSql } from '../reference-flag.ts';
 
 /** Shared shape returned by all four checks. */
 export interface OnboardCheckResult {
@@ -120,7 +121,8 @@ export async function checkEntityLinkCoverage(
     engine,
     `SELECT COUNT(*) AS count FROM pages
        WHERE type IN ('person', 'company', 'organization', 'entity')
-         AND deleted_at IS NULL`,
+         AND deleted_at IS NULL
+         AND ${referenceExclusionSql()}`,
   );
 
   if (totalEntities === 0) {
@@ -144,6 +146,7 @@ export async function checkEntityLinkCoverage(
        SELECT p.id FROM pages p ${sampleClause}
        WHERE p.type IN ('person', 'company', 'organization', 'entity')
          AND p.deleted_at IS NULL
+         AND ${referenceExclusionSql('p')}
          AND EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)
      ) sub`,
   );
@@ -215,7 +218,8 @@ export async function checkTimelineCoverage(
     engine,
     `SELECT COUNT(*) AS count FROM pages
        WHERE type IN ('person', 'company', 'organization', 'entity')
-         AND deleted_at IS NULL`,
+         AND deleted_at IS NULL
+         AND ${referenceExclusionSql()}`,
   );
 
   if (totalEntities === 0) {
@@ -237,6 +241,7 @@ export async function checkTimelineCoverage(
        SELECT p.id FROM pages p ${sampleClause}
        WHERE p.type IN ('person', 'company', 'organization', 'entity')
          AND p.deleted_at IS NULL
+         AND ${referenceExclusionSql('p')}
          AND EXISTS (SELECT 1 FROM timeline_entries t WHERE t.page_id = p.id)
      ) sub`,
   );

src/core/onboard/init-nudge.ts

@@ -14,6 +14,7 @@
 // also short-circuits (CI/scripted callers see nothing).
 
 import type { BrainEngine } from '../engine.ts';
+import { referenceExclusionSql } from '../reference-flag.ts';
 
 const NUDGE_BUDGET_MS = 3000;
 
@@ -57,7 +58,8 @@ export async function runInitNudge(engine: BrainEngine): Promise<void> {
       engine.executeRaw<{ count: string | number }>(
         `SELECT COUNT(*) AS count FROM pages
            WHERE type IN ('person', 'company', 'organization', 'entity')
-             AND deleted_at IS NULL`,
+             AND deleted_at IS NULL
+             AND ${referenceExclusionSql()}`,
         [],
         { signal: controller.signal },
       ),
@@ -65,6 +67,7 @@ export async function runInitNudge(engine: BrainEngine): Promise<void> {
         `SELECT COUNT(*) AS count FROM pages p
            WHERE p.type IN ('person', 'company', 'organization', 'entity')
              AND p.deleted_at IS NULL
+             AND ${referenceExclusionSql('p')}
              AND EXISTS (SELECT 1 FROM links l WHERE l.to_page_id = p.id)`,
         [],
         { signal: controller.signal },
@@ -73,6 +76,7 @@ export async function runInitNudge(engine: BrainEngine): Promise<void> {
         `SELECT COUNT(*) AS count FROM pages p
            WHERE p.type IN ('person', 'company', 'organization', 'entity')
              AND p.deleted_at IS NULL
+             AND ${referenceExclusionSql('p')}
              AND EXISTS (SELECT 1 FROM timeline_entries t WHERE t.page_id = p.id)`,
         [],
         { signal: controller.signal },

src/core/pglite-engine.ts

@@ -23,6 +23,7 @@ import { runMigrations } from './migrate.ts';
 import { PGLITE_SCHEMA_SQL, getPGLiteSchema } from './pglite-schema.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
+import { referenceExclusionSql } from './reference-flag.ts';
 import { MARKDOWN_CHUNKER_VERSION } from './chunkers/recursive.ts';
 import { acquireLock, releaseLock, type LockHandle } from './pglite-lock.ts';
 import { getFtsLanguage } from './fts-language.ts';
@@ -5202,6 +5203,7 @@ export class PGLiteEngine implements BrainEngine {
     const { rows: [h] } = await this.db.query(`
       WITH entity_pages AS (
         SELECT id, slug FROM pages WHERE type IN ('person', 'company')
+          AND ${referenceExclusionSql()}
       )
       SELECT
         (SELECT count(*) FROM pages) as page_count,

src/core/postgres-engine.ts

@@ -5320,7 +5320,12 @@ export class PostgresEngine implements BrainEngine {
     // is working as intended, not an orphan.
     const [h] = await sql`
       WITH entity_pages AS (
+        -- reference:true pages are exempt from coverage metrics.
+        -- Inlined (postgres.js tagged-template interpolation = bound param,
+        -- not raw SQL); keep in sync with referenceExclusionSql() in
+        -- reference-flag.ts.
         SELECT id, slug FROM pages WHERE type IN ('person', 'company')
+          AND (frontmatter->>'reference') IS DISTINCT FROM 'true'
       )
       SELECT
         (SELECT count(*) FROM pages) as page_count,

src/core/reference-flag.ts

@@ -0,0 +1,37 @@
+// Reference / canon entities.
+//
+// A page with frontmatter `reference: true` is a reference-only entity — a
+// figure or organization imported from a book / article / external source that
+// the user reads ABOUT but does not actively interact with (e.g. Andy Grove,
+// Kleiner Perkins). It keeps its real `type` (`person` / `company`), so it stays
+// fully searchable, enrichable, linkable, and edge-resolvable — NOTHING about
+// retrieval changes.
+//
+// The ONLY behavior it opts out of is the entity *coverage* metrics
+// (`timeline_coverage`, `entity_link_coverage` + their onboard-nudge mirrors).
+// Those metrics nudge "this entity should accumulate dated history / inbound
+// links"; that assumption is right for people you actually deal with and wrong
+// for canon imports, which have no dated events in the user's life. Excluding
+// them keeps the metric honest and actionable instead of permanently red.
+//
+// Opt-in: absent / false / anything-but-true = normal entity (the default).
+// Set via `gbrain reference <slug>` (or hand-edit frontmatter).
+
+export const REFERENCE_FRONTMATTER_KEY = 'reference';
+
+/**
+ * SQL predicate (true for NON-reference pages) to AND into entity-coverage
+ * denominators AND numerators so the ratio stays consistent. JSONB `->>` yields
+ * text; `IS DISTINCT FROM 'true'` treats absent (NULL) and every non-true value
+ * as a normal counted entity. Backed by the GIN index on `pages.frontmatter`.
+ *
+ * @param alias optional table alias (e.g. 'p' for `pages p`); omit for bare `pages`.
+ *
+ * NOTE: postgres-engine.ts uses a postgres.js tagged template where `${}` is a
+ * bound parameter, not raw SQL, so it inlines this predicate literally — keep
+ * the two in sync.
+ */
+export function referenceExclusionSql(alias = ''): string {
+  const col = alias ? `${alias}.frontmatter` : 'frontmatter';
+  return `(${col}->>'${REFERENCE_FRONTMATTER_KEY}') IS DISTINCT FROM 'true'`;
+}

test/e2e/obsidian-gbrain-safe-index.test.ts

@@ -1,61 +0,0 @@
-/**
- * E2E smoke for skills/obsidian-gbrain-safe-index.
- *
- * Verifies the from-trigger-to-side-effect path that skillify requires:
- * a real user trigger phrase routes to the skill, the resolver/check
- * pipeline treats it as reachable, and the skill file exposes the
- * gbrain commands the workflow actually runs.
- *
- * This stays local-only (no paid embedding, no external API): it asserts
- * the documented safe/import path is present and parseable, not that it
- * mutates a live brain.
- */
-
-import { describe, expect, it } from 'bun:test';
-import { existsSync, readFileSync } from 'fs';
-import { join } from 'path';
-
-const SKILLS = join(import.meta.dir, '..', '..', 'skills');
-const SKILL_MD = join(SKILLS, 'obsidian-gbrain-safe-index', 'SKILL.md');
-const RESOLVER = join(SKILLS, 'RESOLVER.md');
-
-const TRIGGER_PHRASES = [
-  'connect my Obsidian vault to gbrain',
-  'import my vault to gbrain',
-  'sync vault and gbrain',
-  'capture this skill in my vault',
-  'embed gbrain after vault update',
-  'is gbrain synced with my vault',
-];
-
-describe('obsidian-gbrain-safe-index E2E', () => {
-  it('resolver maps real trigger phrasings to the skill', () => {
-    const resolver = readFileSync(RESOLVER, 'utf-8');
-    expect(resolver).toContain('obsidian-gbrain-safe-index/SKILL.md');
-    // Each representative phrase shares a token substring with a resolver row.
-    const rows = resolver
-      .split('\n')
-      .filter((l) => l.includes('obsidian-gbrain-safe-index/SKILL.md'))
-      .join('\n');
-    for (const phrase of TRIGGER_PHRASES) {
-      const hit = phrase
-        .toLowerCase()
-        .split(/\s+/)
-        .some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
-      expect(hit, `no resolver token for: ${phrase}`).toBe(true);
-    }
-  });
-
-  it('skill documents the gbrain import-first safe path', () => {
-    const body = readFileSync(SKILL_MD, 'utf-8');
-    expect(body).toContain('gbrain import');
-    expect(body).toContain('--no-embed');
-    expect(body).toContain('gbrain config set search.mode conservative');
-    // Paid gate must be explicit, not a silent default.
-    expect(body).toContain('gbrain embed --stale');
-  });
-
-  it('skill is reachable from the skill tree', () => {
-    expect(existsSync(SKILL_MD)).toBe(true);
-  });
-});

test/e2e/skill-vault-capture-policy.test.ts

@@ -1,52 +0,0 @@
-/**
- * E2E smoke for skills/skill-vault-capture-policy.
- *
- * Verifies the from-trigger-to-side-effect path: a real capture request
- * routes to the skill, and the skill documents the vault navigation
- * obligations (index.md / log.md) that make a capture durable.
- *
- * Local-only: it asserts documented behavior, not live vault writes.
- */
-
-import { describe, expect, it } from 'bun:test';
-import { existsSync, readFileSync } from 'fs';
-import { join } from 'path';
-
-const SKILLS = join(import.meta.dir, '..', '..', 'skills');
-const SKILL_MD = join(SKILLS, 'skill-vault-capture-policy', 'SKILL.md');
-const RESOLVER = join(SKILLS, 'RESOLVER.md');
-
-const TRIGGER_PHRASES = [
-  'save this learning to the vault',
-  'capture this skill in Obsidian',
-  'record this workflow in my notes',
-  'put this setup change in the knowledge base',
-];
-
-describe('skill-vault-capture-policy E2E', () => {
-  it('resolver maps real capture phrasings to the skill', () => {
-    const resolver = readFileSync(RESOLVER, 'utf-8');
-    expect(resolver).toContain('skill-vault-capture-policy/SKILL.md');
-    const rows = resolver
-      .split('\n')
-      .filter((l) => l.includes('skill-vault-capture-policy/SKILL.md'))
-      .join('\n');
-    for (const phrase of TRIGGER_PHRASES) {
-      const hit = phrase
-        .toLowerCase()
-        .split(/\s+/)
-        .some((tok) => tok.length > 3 && rows.toLowerCase().includes(tok));
-      expect(hit, `no resolver token for: ${phrase}`).toBe(true);
-    }
-  });
-
-  it('skill documents index.md and log.md update obligations', () => {
-    const body = readFileSync(SKILL_MD, 'utf-8');
-    expect(body).toContain('index.md');
-    expect(body).toContain('log.md');
-  });
-
-  it('skill is reachable from the skill tree', () => {
-    expect(existsSync(SKILL_MD)).toBe(true);
-  });
-});

test/obsidian-gbrain-safe-index.test.ts

@@ -1,51 +0,0 @@
-import { describe, expect, it } from 'bun:test';
-import { readFileSync, existsSync } from 'fs';
-import { join } from 'path';
-
-const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'obsidian-gbrain-safe-index');
-const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
-const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
-
-function parseFrontmatter(raw: string): Record<string, unknown> {
-  const m = raw.match(/^---\n([\s\S]*?)\n---/);
-  if (!m) throw new Error('no frontmatter');
-  const out: Record<string, unknown> = {};
-  for (const line of m[1].split('\n')) {
-    const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
-    if (mm) out[mm[1]] = mm[2].trim();
-  }
-  return out;
-}
-
-describe('obsidian-gbrain-safe-index skill', () => {
-  it('has a SKILL.md with required frontmatter', () => {
-    expect(existsSync(SKILL_MD)).toBe(true);
-    const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
-    expect(fm['name']).toBe('obsidian-gbrain-safe-index');
-    expect(fm['description']).toBeTruthy();
-  });
-
-  it('has the required conformance sections', () => {
-    const body = readFileSync(SKILL_MD, 'utf-8');
-    for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
-      expect(body.includes(section), `missing ${section}`).toBe(true);
-    }
-  });
-
-  it('is registered in RESOLVER.md', () => {
-    expect(existsSync(RESOLVER)).toBe(true);
-    const resolver = readFileSync(RESOLVER, 'utf-8');
-    expect(resolver.includes('obsidian-gbrain-safe-index/SKILL.md')).toBe(true);
-  });
-
-  it('has routing-eval fixtures that exercise real trigger phrasings', () => {
-    const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
-    expect(existsSync(evalPath)).toBe(true);
-    const lines = readFileSync(evalPath, 'utf-8')
-      .split('\n')
-      .filter((l) => l.trim() && !l.trim().startsWith('//'))
-      .map((l) => JSON.parse(l));
-    const positives = lines.filter((l) => l.expected_skill === 'obsidian-gbrain-safe-index');
-    expect(positives.length).toBeGreaterThanOrEqual(5);
-  });
-});

test/reference-flag.test.ts

@@ -0,0 +1,154 @@
+import { describe, expect, test } from 'bun:test';
+import { referenceExclusionSql, REFERENCE_FRONTMATTER_KEY } from '../src/core/reference-flag.ts';
+import { applyReferenceFrontmatter } from '../src/commands/reference.ts';
+
+describe('referenceExclusionSql', () => {
+  test('bare pages (no alias)', () => {
+    expect(referenceExclusionSql()).toBe(`(frontmatter->>'reference') IS DISTINCT FROM 'true'`);
+  });
+  test('aliased', () => {
+    expect(referenceExclusionSql('p')).toBe(`(p.frontmatter->>'reference') IS DISTINCT FROM 'true'`);
+  });
+  test('key constant', () => {
+    expect(REFERENCE_FRONTMATTER_KEY).toBe('reference');
+  });
+});
+
+describe('applyReferenceFrontmatter', () => {
+  const page = `---\ntitle: Andy Grove\ntype: person\ntags: []\n---\n\n# Andy Grove\n\nBody.`;
+
+  test('adds reference: true to an existing frontmatter block', () => {
+    const out = applyReferenceFrontmatter(page, true);
+    expect(out).toContain('reference: true');
+    expect(out).toContain('type: person');   // other keys preserved
+    expect(out).toContain('# Andy Grove');    // body preserved
+  });
+
+  test('is idempotent — does not duplicate the key', () => {
+    const once = applyReferenceFrontmatter(page, true);
+    const twice = applyReferenceFrontmatter(once, true);
+    expect(twice).toBe(once);
+    expect(twice.match(/reference: true/g)).toHaveLength(1);
+  });
+
+  test('replaces a stale reference: false with true', () => {
+    const off = `---\ntype: person\nreference: false\n---\n\nBody.`;
+    const out = applyReferenceFrontmatter(off, true);
+    expect(out).toContain('reference: true');
+    expect(out).not.toContain('reference: false');
+  });
+
+  test('--unset removes the key', () => {
+    const on = applyReferenceFrontmatter(page, true);
+    const off = applyReferenceFrontmatter(on, false);
+    expect(off).not.toContain('reference:');
+    expect(off).toContain('type: person');
+  });
+
+  test('--unset on a page without the key is a no-op', () => {
+    expect(applyReferenceFrontmatter(page, false)).toBe(page);
+  });
+
+  test('setting on a frontmatter-less page prepends a block', () => {
+    const raw = '# Just a heading\n\nNo frontmatter here.';
+    const out = applyReferenceFrontmatter(raw, true);
+    expect(out.startsWith('---\nreference: true\n---\n')).toBe(true);
+    expect(out).toContain('# Just a heading');
+  });
+
+  test('preserves body containing YAML-special chars', () => {
+    const tricky = `---\ntype: person\n---\n\nText with $& and $1 literals.`;
+    const out = applyReferenceFrontmatter(tricky, true);
+    expect(out).toContain('Text with $& and $1 literals.');
+    expect(out).toContain('reference: true');
+  });
+});
+
+// ── e2e: getHealth exemption + (source_id, slug)-scoped JSONB write ─────────
+
+import { afterAll, beforeAll } from 'bun:test';
+import * as fs from 'node:fs';
+import * as os from 'node:os';
+import * as path from 'node:path';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { runReference } from '../src/commands/reference.ts';
+import { withEnv } from './helpers/with-env.ts';
+
+describe('reference flag e2e (PGLite)', () => {
+  let engine: PGLiteEngine;
+  let brainDir: string;
+
+  beforeAll(async () => {
+    engine = new PGLiteEngine();
+    await engine.connect({ database_url: '' });
+    await engine.initSchema();
+
+    brainDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gbrain-ref-'));
+    fs.mkdirSync(path.join(brainDir, 'people'), { recursive: true });
+    fs.writeFileSync(
+      path.join(brainDir, 'people/andy-grove.md'),
+      '---\ntitle: Andy Grove\ntype: person\n---\n\n# Andy Grove\n',
+      'utf8',
+    );
+
+    await engine.executeRaw(
+      `INSERT INTO sources (id, name, local_path, config, created_at)
+       VALUES ('src-a', 'a', $1, '{}'::jsonb, now()), ('src-b', 'b', NULL, '{}'::jsonb, now())`,
+      [brainDir],
+    );
+    // Same slug in BOTH sources — the write must only touch src-a.
+    await engine.putPage('people/andy-grove', {
+      type: 'person', title: 'Andy Grove', compiled_truth: 'canon figure',
+    }, { sourceId: 'src-a' });
+    await engine.putPage('people/andy-grove', {
+      type: 'person', title: 'Andy Grove', compiled_truth: 'other-source twin',
+    }, { sourceId: 'src-b' });
+    // A normal contact WITH a timeline entry, so coverage has a live numerator.
+    const contact = await engine.putPage('people/alice-example', {
+      type: 'person', title: 'Alice Example', compiled_truth: 'real contact',
+    }, { sourceId: 'src-a' });
+    await engine.executeRaw(
+      `INSERT INTO timeline_entries (page_id, date, summary) VALUES ($1, '2026-01-01', 'met')`,
+      [contact.id],
+    );
+  });
+
+  afterAll(async () => {
+    await engine.disconnect();
+    fs.rmSync(brainDir, { recursive: true, force: true });
+  });
+
+  test('runReference scopes the JSONB write to the resolved (source_id, slug)', async () => {
+    await withEnv({ GBRAIN_SOURCE: undefined }, () =>
+      runReference(engine, ['people/andy-grove', '--brain', brainDir]));
+
+    const rows = await engine.executeRaw<{ source_id: string; ref: string | null }>(
+      `SELECT source_id, frontmatter->>'reference' AS ref FROM pages WHERE slug = 'people/andy-grove' ORDER BY source_id`,
+    );
+    expect(rows).toEqual([
+      { source_id: 'src-a', ref: 'true' },
+      { source_id: 'src-b', ref: null },   // twin in the other source untouched
+    ]);
+    // Durable half: frontmatter on disk got the flag too.
+    expect(fs.readFileSync(path.join(brainDir, 'people/andy-grove.md'), 'utf8'))
+      .toContain('reference: true');
+  });
+
+  test('getHealth exempts reference pages from timeline/link coverage', async () => {
+    const health = await engine.getHealth();
+    // 3 person pages; the 2 reference-less twins would drag coverage to 1/3.
+    // With the src-a twin marked reference, denominator = 2 (alice + src-b twin).
+    expect(health.timeline_coverage).toBeCloseTo(0.5);
+  });
+
+  test('unset restores the page to a normal counted entity', async () => {
+    await withEnv({ GBRAIN_SOURCE: undefined }, () =>
+      runReference(engine, ['people/andy-grove', '--unset', '--brain', brainDir]));
+    const rows = await engine.executeRaw<{ ref: string | null }>(
+      `SELECT frontmatter->>'reference' AS ref FROM pages WHERE slug = 'people/andy-grove' AND source_id = 'src-a'`,
+    );
+    expect(rows[0].ref).toBeNull();
+    const health = await engine.getHealth();
+    expect(health.timeline_coverage).toBeCloseTo(1 / 3);
+  });
+});

test/skill-vault-capture-policy.test.ts

@@ -1,64 +0,0 @@
-import { describe, expect, it } from 'bun:test';
-import { readFileSync, existsSync } from 'fs';
-import { join } from 'path';
-import { DEFAULT_PRIVATE_PATTERNS } from '../src/core/skillpack/harvest-lint.ts';
-
-const SKILL_DIR = join(import.meta.dir, '..', 'skills', 'skill-vault-capture-policy');
-const SKILL_MD = join(SKILL_DIR, 'SKILL.md');
-const RESOLVER = join(import.meta.dir, '..', 'skills', 'RESOLVER.md');
-
-function parseFrontmatter(raw: string): Record<string, unknown> {
-  const m = raw.match(/^---\n([\s\S]*?)\n---/);
-  if (!m) throw new Error('no frontmatter');
-  const out: Record<string, unknown> = {};
-  for (const line of m[1].split('\n')) {
-    const mm = line.match(/^([a-zA-Z_]+):\s*(.*)$/);
-    if (mm) out[mm[1]] = mm[2].trim();
-  }
-  return out;
-}
-
-describe('skill-vault-capture-policy skill', () => {
-  it('has a SKILL.md with required frontmatter', () => {
-    expect(existsSync(SKILL_MD)).toBe(true);
-    const fm = parseFrontmatter(readFileSync(SKILL_MD, 'utf-8'));
-    expect(fm['name']).toBe('skill-vault-capture-policy');
-    expect(fm['description']).toBeTruthy();
-  });
-
-  it('has the required conformance sections', () => {
-    const body = readFileSync(SKILL_MD, 'utf-8');
-    for (const section of ['## Contract', '## Phases', '## Output Format', '## Anti-Patterns']) {
-      expect(body.includes(section), `missing ${section}`).toBe(true);
-    }
-  });
-
-  it('is registered in RESOLVER.md', () => {
-    expect(existsSync(RESOLVER)).toBe(true);
-    expect(readFileSync(RESOLVER, 'utf-8').includes('skill-vault-capture-policy/SKILL.md')).toBe(true);
-  });
-
-  it('contains no private user or agent-fork names (privacy rule)', () => {
-    for (const file of [SKILL_MD, join(SKILL_DIR, 'routing-eval.jsonl')]) {
-      const body = readFileSync(file, 'utf-8');
-      // DEFAULT_PRIVATE_PATTERNS[0] is the banned fork-name pattern; sourced
-      // from harvest-lint so this file never contains the literal itself
-      // (scripts/check-privacy.sh would reject it).
-      const forkName = new RegExp(DEFAULT_PRIVATE_PATTERNS[0], 'i');
-      for (const name of [/\bAdam\b/, /\bHermes\b/, /\bHerdr\b/, /\bArk\b/, forkName]) {
-        expect(name.test(body), `private name ${name} in ${file}`).toBe(false);
-      }
-    }
-  });
-
-  it('has routing-eval fixtures', () => {
-    const evalPath = join(SKILL_DIR, 'routing-eval.jsonl');
-    expect(existsSync(evalPath)).toBe(true);
-    const positives = readFileSync(evalPath, 'utf-8')
-      .split('\n')
-      .filter((l) => l.trim() && !l.trim().startsWith('//'))
-      .map((l) => JSON.parse(l))
-      .filter((l) => l.expected_skill === 'skill-vault-capture-policy');
-    expect(positives.length).toBeGreaterThanOrEqual(4);
-  });
-});