@event4u/agent-config 14.22.0 → 15.0.0

package/dist/agent-src/commands/ghostwriter/write.md

@@ -20,7 +20,7 @@ packs:
 
 Generate a copyable markdown draft in the voice of a captured
 ghostwriter profile under `agents/reference/ghostwriter/<slug>.md`. Implements
-the [`write-engine`](../../../docs/contracts/write-engine.md) contract
+the [`write-engine`](../../docs/contracts/write-engine.md) contract
 with **mandatory disclosure footer** appended by this command's output
 template (not by the model, no opt-out).
 
@@ -40,7 +40,7 @@ Argument shapes:
 `<value>` resolves against **slugs** and (when
 `ghostwriter.aliases: true` in `.agent-project-settings.yml` — default
 on) the `aliases:` list of every consumer profile. See
-[`ghostwriter-schema § Aliases`](../../../docs/contracts/ghostwriter-schema.md#aliases).
+[`ghostwriter-schema § Aliases`](../../docs/contracts/ghostwriter-schema.md#aliases).
 
 Scan `agents/reference/ghostwriter/*.md`, excluding `README.md` and any file
 with `fictional: true` (fixtures are not consumable from this
@@ -68,7 +68,7 @@ User picks by number or value. No default — explicit choice required.
 ### 2. Load the style source
 
 Read the selected file's frontmatter. Required keys (per
-[`ghostwriter-schema`](../../../docs/contracts/ghostwriter-schema.md)):
+[`ghostwriter-schema`](../../docs/contracts/ghostwriter-schema.md)):
 `identity.name`, `style.fingerprint.*`, `style.free_form_notes`,
 `voice_samples`, `taboos`, `source_provenance.verification`.
 
@@ -78,7 +78,7 @@ Style fidelity may be lower."* Non-blocking.
 
 ### 3. Collect topic + modifiers
 
-Per [`write-engine § 2`](../../../docs/contracts/write-engine.md).
+Per [`write-engine § 2`](../../docs/contracts/write-engine.md).
 Flag form: `--tone=<formal|casual|neutral>`,
 `--length=<words>`, `--channel=<linkedin-post|tweet|blog|freeform>`,
 `--audience=<text>`. The channel values and their length defaults are
@@ -93,13 +93,13 @@ and the vocab-register → tone mapping in the engine contract.
 ### 4. Negative-constraint pass
 
 Apply the loaded `taboos` list as exclusions before drafting (per
-[`write-engine § 3`](../../../docs/contracts/write-engine.md)). Print
+[`write-engine § 3`](../../docs/contracts/write-engine.md)). Print
 a one-line acknowledgement: *"Excluding N taboos from this profile."*
 
 ### 5. Draft
 
 Generate the body as a single fenced markdown block per
-[`write-engine § 4`](../../../docs/contracts/write-engine.md). Honour
+[`write-engine § 4`](../../docs/contracts/write-engine.md). Honour
 fingerprint constraints: sentence-length ±25 %, opener / closer
 patterns, hashtag / emoji rules, ±15 % length tolerance.
 
@@ -116,7 +116,7 @@ This footer is appended **by this command's output template** as a
 fixed string. It is not produced by the model. No `--no-disclosure`
 flag, no `--internal` flag, no opt-out. The absence of any such flag
 is the acceptance criterion (locked in
-[`ghostwriter-schema`](../../../docs/contracts/ghostwriter-schema.md)
+[`ghostwriter-schema`](../../docs/contracts/ghostwriter-schema.md)
 § Mandatory disclosure footer).
 
 **The footer always uses `identity.name`, never the alias that
@@ -161,8 +161,8 @@ Non-blocking.
 
 ## See also
 
-- [`write-engine`](../../../docs/contracts/write-engine.md) — shared procedural contract.
-- [`ghostwriter-schema`](../../../docs/contracts/ghostwriter-schema.md) — locked v1 frontmatter.
+- [`write-engine`](../../docs/contracts/write-engine.md) — shared procedural contract.
+- [`ghostwriter-schema`](../../docs/contracts/ghostwriter-schema.md) — locked v1 frontmatter.
 - [`/ghostwriter`](../ghostwriter.md) — parent cluster.
 - [`/ghostwriter:fetch`](fetch.md) — the producer side.
 - [`/post-as:ghostwriter`](../post-as/ghostwriter.md) — thin alias for this command.

package/dist/agent-src/commands/humanize.md

@@ -19,7 +19,7 @@ packs:
 
 # /humanize
 
-Run the [`humanizer`](../../../src/skills/humanizer/SKILL.md) skill's
+Run the [`humanizer`](../skills/humanizer/SKILL.md) skill's
 full draft→audit→final loop on a piece of deliverable prose. On-demand
 counterpart to the write-engine's built-in step 4b audit.
 
@@ -34,7 +34,7 @@ counterpart to the write-engine's built-in step 4b audit.
 - `/humanize <path>` — read the file at `<path>` (read-only).
 - `/humanize --voice=<ghostwriter-slug|me>` — optionally resolve a voice
   via the write-engine's style-source resolution (§ 1 of the
-  [`write-engine`](../../docs/contracts/write-engine.md) contract):
+  [`write-engine`](../docs/contracts/write-engine.md) contract):
   a ghostwriter slug loads `agents/reference/ghostwriter/<slug>.md`, `me`
   loads `.agent-user.md`. The resolved fingerprint takes precedence over
   humanizer defaults (a voice that legitimately uses em dashes wins). No
@@ -88,7 +88,7 @@ because it produces no text at all.
 
 ### 2. Run the humanizer loop
 
-Follow [`humanizer § Procedure`](../../../src/skills/humanizer/SKILL.md):
+Follow [`humanizer § Procedure`](../skills/humanizer/SKILL.md):
 load `data/patterns.md`, draft the rewrite (full coverage, voice
 precedence: fingerprint > brand voice > defaults), audit ("what still
 reads AI-generated?"), final rewrite.
@@ -137,9 +137,9 @@ Default form:
 
 ## See also
 
-- [`humanizer`](../../../src/skills/humanizer/SKILL.md) — the skill this
+- [`humanizer`](../skills/humanizer/SKILL.md) — the skill this
   command wraps.
-- [`write-engine § 4b`](../../docs/contracts/write-engine.md) — the
+- [`write-engine § 4b`](../docs/contracts/write-engine.md) — the
   built-in audit for ghostwriter/post-as drafts.
-- [`content-quoting-floor`](../../../src/rules/content-quoting-floor.md)
+- [`content-quoting-floor`](../rules/content-quoting-floor.md)
   — quoted text is never rewritten.

package/dist/agent-src/commands/jira-ticket.md

@@ -81,4 +81,4 @@ packs:
 
 ## See also
 
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract (Goal / Plan / Changes / Tests / Open questions)
+- [`role-contracts`](../guidelines/agent-infra/role-contracts.md#developer) — Developer mode output contract (Goal / Plan / Changes / Tests / Open questions)

package/dist/agent-src/commands/judge/solo.md

@@ -94,4 +94,4 @@ Next step: <what the user should do based on the verdict>
 - [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md)
 - [`/judge on-diff`](do-and-judge.md) — if a revision loop is wanted
 - [`/review-changes`](review-changes.md) — human-oriented self-review
-- [`role-contracts`](../../docs/guidelines/agent-infra/role-contracts.md#reviewer) — Reviewer mode output contract (Summary / Risks / Findings / Required actions / Verdict)
+- [`role-contracts`](../../guidelines/agent-infra/role-contracts.md#reviewer) — Reviewer mode output contract (Summary / Risks / Findings / Required actions / Verdict)

package/dist/agent-src/commands/judge.md

@@ -84,4 +84,4 @@ the implementer loop, so it never fires on a bare safe-default fallback.
 
 - [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md)
 - [`/review`](review-changes.md) — human-oriented self-review (Reviewer-mode contract)
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md#reviewer)
+- [`role-contracts`](../guidelines/agent-infra/role-contracts.md#reviewer)

package/dist/agent-src/commands/knowledge/cross-repo.md

@@ -23,7 +23,7 @@ Targeted, **read-only** retrieval across the IDE-attached sibling repos the user
 has opted into (`linked_projects[].include: true`). Returns a bounded set of
 matches — a shared type, an API contract the frontend consumes, a config the
 sibling owns — **without bulk-including** any sibling file. Implements
-[`cross-repo-retrieval`](../../../docs/contracts/cross-repo-retrieval.md) and
+[`cross-repo-retrieval`](../../docs/contracts/cross-repo-retrieval.md) and
 stays inside [ADR-032](../../../docs/decisions/ADR-032-linked-projects-scope.md)
 Option A.
 

package/dist/agent-src/commands/knowledge/forget.md

@@ -93,5 +93,5 @@ If the prefix matched multiple ingests:
 
 - [`/knowledge ingest`](ingest.md) — add a new ingest.
 - [`/knowledge list`](list.md) — find an id prefix.
-- [`local-knowledge-ingestion`](../../../docs/contracts/local-knowledge-ingestion.md)
+- [`local-knowledge-ingestion`](../../docs/contracts/local-knowledge-ingestion.md)
   § Storage — directory layout.

package/dist/agent-src/commands/knowledge/ingest.md

@@ -21,7 +21,7 @@ packs:
 
 Indexes a local path into the agent's memory namespace. Local-only,
 single-user, bounded. Implements the
-[`local-knowledge-ingestion`](../../../docs/contracts/local-knowledge-ingestion.md)
+[`local-knowledge-ingestion`](../../docs/contracts/local-knowledge-ingestion.md)
 contract.
 
 ## Prerequisites
@@ -107,7 +107,7 @@ Show the user how to retrieve:
 
 ## See also
 
-- [`local-knowledge-ingestion`](../../../docs/contracts/local-knowledge-ingestion.md)
+- [`local-knowledge-ingestion`](../../docs/contracts/local-knowledge-ingestion.md)
   — contract (input shapes, bounds, storage, redaction).
 - [`/knowledge list`](list.md) — what's been ingested, pinning.
 - [`/knowledge forget`](forget.md) — drop an ingest atomically.

package/dist/agent-src/commands/knowledge/list.md

@@ -100,5 +100,5 @@ user has already provided. See also
 
 - [`/knowledge ingest`](ingest.md) — add a new ingest.
 - [`/knowledge forget`](forget.md) — drop an ingest atomically.
-- [`local-knowledge-ingestion`](../../../docs/contracts/local-knowledge-ingestion.md)
+- [`local-knowledge-ingestion`](../../docs/contracts/local-knowledge-ingestion.md)
   § Bounds — when LRU fires.

package/dist/agent-src/commands/memory/add.md

@@ -20,7 +20,7 @@ packs:
 Creates or updates a single entry in one of the four engineering-memory
 YAML files under `agents/memory/` in the consumer project. The entry
 is validated against the schema in
-[`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md)
+[`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md)
 before the file is written.
 
 Absence of these files is legal — this command is the entry point for
@@ -65,7 +65,7 @@ sharded layout: `agents/memory/<type>/*.yml`). For each existing
 ### 3. Collect the required fields
 
 All four types share the frontmatter in
-[`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md#shared-frontmatter-fields).
+[`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md#shared-frontmatter-fields).
 Collect in this order, one numbered question at a time:
 
 1. `id` — kebab-case slug, unique within the type.
@@ -140,7 +140,7 @@ Read `verbosity.post_action_reports` from `.agent-settings.yml` (default
 
 ## See also
 
-- [`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md)
+- [`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md)
   — full schema
 - [`skill:learning-to-rule-or-skill`](../skills/learning-to-rule-or-skill/SKILL.md) —
   when a learning is better captured as an `incident-learnings` entry vs

package/dist/agent-src/commands/memory/load.md

@@ -122,7 +122,7 @@ opts in.
 
 The agent should now treat every loaded entry as an authority signal
 with its declared `confidence` — see
-[`memory-access`](../../docs/guidelines/agent-infra/memory-access.md) for
+[`memory-access`](../../guidelines/agent-infra/memory-access.md) for
 how entries modulate edits.
 
 ### 5. Inline-review hook (intake backlog)
@@ -184,8 +184,8 @@ When resolving a knowledge/memory read — including cross-project access — cl
 the ladder and stop at the first rung that answers; do not jump straight to a
 full scan:
 
-1. **Hot cache** — the already-loaded session slice (`hot-context.md` / the
-   Tier-0 slice above); zero new reads.
+1. **Already loaded** — the session slice already in context (the Tier-0 slice
+   above, plus the `session_start` memory index when armed); zero new reads.
 2. **Index** — the lexical index / `memory_lookup retrieve_v1` over the keys.
 3. **Type index** — narrow to the relevant type directory, then its entries.
 4. **Entry** — read the specific entry only once the first three located it.
@@ -198,5 +198,5 @@ nothing on this" — never invent an entry to fill the gap.
 - [`memory-add`](memory-add.md) — add a single entry
 - [`memory-promote`](memory-promote.md) — promote an intake signal to
   a curated entry
-- [`memory-access`](../../docs/guidelines/agent-infra/memory-access.md) —
+- [`memory-access`](../../guidelines/agent-infra/memory-access.md) —
   how entries flow into agent decisions

package/dist/agent-src/commands/memory/mine-session.md

@@ -180,5 +180,5 @@ Confirm:
   `TranscriptAdapter` matches the current host.
 - [`memory:promote`](promote.md) — lifts validated intake lines into
   curated YAML.
-- [`memory-access`](../../../docs/guidelines/agent-infra/memory-access.md) —
+- [`memory-access`](../../guidelines/agent-infra/memory-access.md) —
   file-backed retrieval contract for curated + intake entries.

package/dist/agent-src/commands/memory/promote.md

@@ -69,7 +69,7 @@ gate script to lower the bar.
 ### 3. Draft the curated entry
 
 Using the schema in
-[`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md),
+[`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md),
 hydrate the full frontmatter:
 
 - `id` — kebab-case slug (not the `sig-*` id — that is an intake marker).
@@ -83,7 +83,7 @@ hydrate the full frontmatter:
   on every `/memory:load` regardless of query — e.g. a tenant-isolation
   invariant or a payment-flow rule. The validator warns when a type
   accumulates more than 10 active critical entries; raise the bar
-  deliberately. See [`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md)
+  deliberately. See [`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md)
   § Priority semantics for the full contract.
 - `ts_week:` — optional ISO-week stamp `YYYY-Www` (e.g. `2026-W17`).
   **Convention, not enforced.** Stamp the curated entry with the week
@@ -94,7 +94,7 @@ hydrate the full frontmatter:
   ```bash
   date -u +'%G-W%V'   # POSIX ISO week-numbering year + ISO week
   ```
-  See [`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md)
+  See [`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md)
   § Temporal jitter for rationale.
 - Type-specific fields (`rule`, `symptom`, `path`, …).
 
@@ -236,4 +236,4 @@ Read `verbosity.post_action_reports` from `.agent-settings.yml` (default
 
 - [`/propose-memory`](propose-memory.md) — write-side entry point.
 - [`/memory-add`](memory-add.md) — direct curated write (skips intake).
-- [`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md)
+- [`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md)

package/dist/agent-src/commands/memory/propose.md

@@ -131,6 +131,6 @@ is intended (rarely).
 ## See also
 
 - [`/memory-add`](memory-add.md) — curated (reviewer-validated) entries.
-- [`engineering-memory-data-format`](../../docs/guidelines/agent-infra/engineering-memory-data-format.md)
-- [`memory-access`](../../docs/guidelines/agent-infra/memory-access.md) — the
+- [`engineering-memory-data-format`](../../guidelines/agent-infra/engineering-memory-data-format.md)
+- [`memory-access`](../../guidelines/agent-infra/memory-access.md) — the
   read-side contract that consumes what this command writes.

package/dist/agent-src/commands/mode.md

@@ -21,7 +21,7 @@ packs:
 
 Sets `roles.active_role` in `.agent-settings.yml` and surfaces the active
 contract before any work. Six modes are defined in
-[`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md):
+[`role-contracts`](../guidelines/agent-infra/role-contracts.md):
 
 - `developer` · `reviewer` · `tester` · `po` · `incident` · `planner`
 
@@ -47,7 +47,7 @@ Anything else: refuse. List the valid values and stop.
 
 ### 2. Validate the mode name
 
-Read [`role-contracts.md`](../docs/guidelines/agent-infra/role-contracts.md).
+Read [`role-contracts.md`](../guidelines/agent-infra/role-contracts.md).
 Extract H3 headings under `## Contract skeletons` and lowercase them.
 If `<name>` is not in that set, refuse and print the valid list.
 
@@ -74,7 +74,7 @@ exactly what the contract demands.
 ### 5. Write the active role
 
 Update `roles.active_role` in `.agent-settings.yml` using the
-[section-aware merge rules](../docs/guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
+[section-aware merge rules](../guidelines/agent-infra/layered-settings.md#section-aware-merge-rules)
 (preserve comments, preserve key order, touch only the changed field).
 
 For `/mode none`: set `active_role: ""`.
@@ -132,7 +132,7 @@ For `/mode` (status only):
 
 ## See also
 
-- [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md) — the six modes
+- [`role-contracts`](../guidelines/agent-infra/role-contracts.md) — the six modes
 - [`role-mode-adherence`](../rules/role-mode-adherence.md) — closing-output gate
-- [`layered-settings`](../docs/guidelines/agent-infra/layered-settings.md) — merge rules for settings edits
+- [`layered-settings`](../guidelines/agent-infra/layered-settings.md) — merge rules for settings edits
 - [`ask-when-uncertain`](../rules/ask-when-uncertain.md) — never invent modes

package/dist/agent-src/commands/post-as/ghostwriter.md

@@ -46,7 +46,7 @@ re-implement, do not skip, do not add steps.
 ### 2. Disclosure footer (mandatory — inherited from `/ghostwriter:write`)
 
 The footer is appended by `/ghostwriter:write`'s output template (per
-[`write-engine § 5`](../../../docs/contracts/write-engine.md)). This
+[`write-engine § 5`](../../docs/contracts/write-engine.md)). This
 alias inherits the footer unconditionally — no `--no-disclosure`
 flag, no `--internal` flag, no opt-out. Any flag that would suppress
 it is forbidden by design.
@@ -68,5 +68,5 @@ it is forbidden by design.
 - [`/ghostwriter:write`](../ghostwriter/write.md) — canonical implementation; this file is a thin alias.
 - [`/post-as`](../post-as.md) — parent cluster.
 - [`/post-as:me`](me.md) — sibling consumer, user-self voice, no footer.
-- [`write-engine`](../../../docs/contracts/write-engine.md) — shared procedural contract.
-- [`ghostwriter-schema`](../../../docs/contracts/ghostwriter-schema.md) — locked v1 frontmatter.
+- [`write-engine`](../../docs/contracts/write-engine.md) — shared procedural contract.
+- [`ghostwriter-schema`](../../docs/contracts/ghostwriter-schema.md) — locked v1 frontmatter.

package/dist/agent-src/commands/post-as/me.md

@@ -21,7 +21,7 @@ packs:
 
 Generate a copyable markdown draft in the **maintainer's own voice**.
 Style source is the project-root `.agent-user.md` file. Implements
-the [`write-engine`](../../../docs/contracts/write-engine.md)
+the [`write-engine`](../../docs/contracts/write-engine.md)
 contract — **the disclosure footer is omitted** because the user is
 the author.
 
@@ -43,7 +43,7 @@ Look in the project root.
 | File exists with `voice_sample` | Proceed |
 
 Schema reference:
-[`agent-user-schema`](../../../docs/contracts/agent-user-schema.md).
+[`agent-user-schema`](../../docs/contracts/agent-user-schema.md).
 
 ### 2. Load the style source
 
@@ -72,7 +72,7 @@ operator notes, not voice signal.
 
 ### 3. Collect topic + modifiers
 
-Per [`write-engine § 2`](../../../docs/contracts/write-engine.md).
+Per [`write-engine § 2`](../../docs/contracts/write-engine.md).
 Flag form: `--tone=<formal|casual|neutral>`,
 `--length=<words>`, `--channel=<linkedin-post|tweet|blog|freeform>`,
 `--audience=<text>`. The channel values and their length defaults are
@@ -87,12 +87,12 @@ the pace mapping above.
 ### 4. Negative-constraint pass (skipped)
 
 `.agent-user.md` v1 has no `taboos` field. Skip per
-[`write-engine § 3`](../../../docs/contracts/write-engine.md).
+[`write-engine § 3`](../../docs/contracts/write-engine.md).
 
 ### 5. Draft
 
 Generate the body as a single fenced markdown block per
-[`write-engine § 4`](../../../docs/contracts/write-engine.md). Honour
+[`write-engine § 4`](../../docs/contracts/write-engine.md). Honour
 the loaded fingerprint (sentence-length ±25 %, pace),
 ±15 % length tolerance, write in `language`.
 
@@ -126,8 +126,8 @@ commit, no save. The user copies the output manually.
 
 ## See also
 
-- [`write-engine`](../../../docs/contracts/write-engine.md) — shared procedural contract.
-- [`agent-user-schema`](../../../docs/contracts/agent-user-schema.md) — `.agent-user.md` source schema.
+- [`write-engine`](../../docs/contracts/write-engine.md) — shared procedural contract.
+- [`agent-user-schema`](../../docs/contracts/agent-user-schema.md) — `.agent-user.md` source schema.
 - [`/post-as`](../post-as.md) — parent cluster.
 - [`/post-as:ghostwriter`](ghostwriter.md) — sibling consumer, public-figure voice, mandatory footer.
 - [`/agents:user:init`](../agents/user/init.md) — bootstrap `.agent-user.md`.

package/dist/agent-src/commands/pr/create.md

@@ -227,7 +227,7 @@ runs on the post-archival state (the findings artifact references
 post-archival paths), (3) the PR is created only with a valid findings
 artifact, honest-null, or skip declaration **for the current review-scope
 hash** per
-[`plan-review-gates § 2`](../../../docs/contracts/plan-review-gates.md).
+[`plan-review-gates § 2`](../../docs/contracts/plan-review-gates.md).
 
 - A completion-review artifact from the roadmap-completion event
   (`agents/evidence/reviews/<slug>.findings.md`) is re-used when its

package/dist/agent-src/commands/pr/merge.md

@@ -4,13 +4,13 @@ name: git-pr-merge
 disable-model-invocation: true
 argument-hint: "[all|<pr-number>] [--no-merge]"
 pack: git
-intent: "Prepare an open PR to mergeable — sync the base in, resolve conflicts semantically, drive required checks green — merging itself is gated and inert"
+intent: "Prepare an open PR to mergeable — sync the base in, resolve conflicts semantically, drive required checks green — then merge what the invocation named"
 routes_to: [git-workflow, github-ci]
 replaces: []
 visibility: advanced
 cluster: git-pr-merge
 skills: [git-workflow, github-ci]
-description: Prepare one open PR to mergeable, or the whole open-PR queue with `all` — merging is specified but gated, so today every invocation stops at mergeable-and-open
+description: Prepare one open PR to mergeable, or the whole open-PR queue with `all`, then merge what the invocation named — `--no-merge` stops at mergeable-and-open
 suggestion:
   eligible: false
   rationale: "Merging is irreversible and gated on the user's own word in the invocation — a suggested merge would manufacture the authorization the Hard Floor requires the user to give."
@@ -28,10 +28,13 @@ green on the head that will actually be merged — and then merge it, if and onl
 if the invocation authorised that.
 
 ```
-THE MERGE STEP (§ 9) IS SPECIFIED AND NOT YET ACTIVE. `--no-merge` IS THE
-OPERATIVE PATH TODAY, AND A BARE INVOCATION BEHAVES AS IF IT CARRIED IT.
-ACTIVATION NEEDS THE OWNER DECISION IN THE `merge-authority` BLOCKER OF
-`road-to-drain-commands` — NEVER A COMMAND EDIT, AND NEVER A GUARD EDIT.
+THE MERGE STEP (§ 9) IS ACTIVE. THE OWNER AUTHORISED IT ON 2026-09-08 AND
+ADR-266 RECORDS THE AMENDMENT TO ADR-237 § 4 THAT ACTIVATED IT — THAT RECORD
+IS WHAT ACTIVATED IT, NEVER A COMMAND EDIT AND NEVER A GUARD EDIT.
+AN EXPLICIT `/pr:merge` INVOCATION IS THE THIS-TURN CONFIRMATION, AND IT
+REACHES EXACTLY THE PRs § 1's MANIFEST SNAPSHOTTED FROM IT. IT NEVER REACHES
+A PR THAT ARRIVED LATER, A HEAD THE MANIFEST DID NOT RECORD, OR ANY OTHER
+HARD-FLOOR ACTION. `--no-merge` STILL STOPS BEFORE § 9.
 ```
 
 **The invocation is the authorization, and nothing else is.** `pr-merge` is
@@ -42,11 +45,12 @@ authorized, and this command still reads it as an audit trail; it introduces no
 second authorization store, and it never writes one. When the work left is
 outside what the owner authorized, the run stops and reports (§ 7).
 
-Why it ships inert rather than not at all: everything before § 9 — the target
-manifest, the four conflict classes, the superseded check, the bounded CI
-repair, the cutoff — is the expensive, error-prone half, it is what the live
-runs actually proved, and none of it merges anything. `--no-merge` delivers all
-of it today.
+Why the preparation half is still the bulk of this command: everything before
+§ 9 — the target manifest, the four conflict classes, the superseded check, the
+bounded CI repair, the cutoff — is the expensive, error-prone part, and it is
+what the live runs actually proved. `--no-merge` delivers exactly that half to
+callers that want it, [`/roadmap:process-full`](../../../product-basic/roadmap/process-full/command.md)
+among them.
 
 ## Sub-commands
 
@@ -56,21 +60,22 @@ of it today.
 *(none, deliberately.)* `all` changes **cardinality**, not lifecycle, so it is
 an argument rather than a second command — the locked registry's rule that
 "sibling variants become a flag, never a second command"
-([`command-clusters`](../../../../../docs/contracts/command-clusters.md)) applied
+([`command-clusters`](../../docs/contracts/command-clusters.md)) applied
 to this cluster. A future sub belongs here only if it has a materially
 different lifecycle, not a different count.
 
 ## Dispatch
 
-Every row below **prepares** — the merge step is gated (see the banner above),
-so today every row ends at mergeable-and-open. The column says what each row
-selects, not that it merges.
+Every row below **prepares** first; the last column says whether it then
+merges. A row that merges reaches only the PRs its own manifest snapshotted
+(§ 1), and only once that PR's required checks are green on the head being
+merged (§ 5).
 
 | Invocation | Selects | Prepares | Merges |
 |---|---|---|---|
-| `/pr:merge <N>` | exactly PR N | yes | only once the gate opens |
-| `/pr:merge` | ONE PR: green first, then infrastructure/tooling before content, then smallest diff (`changedFiles`, then additions+deletions), tiebreak ascending number | yes | only once the gate opens |
-| `/pr:merge all` | the whole open-PR list, under § 6's cutoff | yes | only once the gate opens |
+| `/pr:merge <N>` | exactly PR N | yes | yes — PR N |
+| `/pr:merge` | ONE PR: green first, then infrastructure/tooling before content, then smallest diff (`changedFiles`, then additions+deletions), tiebreak ascending number | yes | yes — the one PR it selected |
+| `/pr:merge all` | the whole open-PR list, under § 6's cutoff | yes | yes — the manifest, in queue order |
 | `… --no-merge` | as above | yes | **never**, explicitly. This is the form [`/roadmap:process-full`](../../../product-basic/roadmap/process-full/command.md) calls for its delivery loop. |
 
 **Bare invocation** (`/pr:merge` with no argument) is a **documented default
@@ -81,7 +86,7 @@ to pick would hand back a decision the command can compute. When the open-PR
 list is empty there is nothing to select and the command reports that and
 stops.
 
-## 1. Snapshot the target — an immutable manifest
+## 1. Snapshot the target — a manifest re-checked before every merge
 
 Compute the queue ONCE at invocation and record it as a manifest of
 `(PR number, head SHA)` pairs:
@@ -102,7 +107,11 @@ other than this run" is undetectable without a base SHA to compare against.
 cap truncated.
 
 The manifest is the authorization's target set and is **never silently
-refreshed by a third party's push**. It is, by design, advanced by *this run's
+refreshed by a third party's push**. It lives in this run's own context and in
+no file, so nothing verifies it and no gate would notice if it drifted — what
+actually binds the target is the pre-merge re-read below, a check that fires,
+not a property that holds. Say "re-checked", never "immutable" (ADR-266
+§ What this record does not claim, finding 3). It is, by design, advanced by *this run's
 own* commits — § 2 merges the base in and § 5 pushes, so a prepared PR's head
 is never the snapshot head, and a naive "refuse when the SHA moved" check would
 fire on every PR the run touches.
@@ -195,11 +204,12 @@ AND RECORD IT AS `blocked-external`.
 ```
 
 The asymmetry is deliberate and worth stating, because it looks inconsistent:
-merging is gated on an owner *decision* recorded once in a blocker, while
-closing is gated on a *per-object* confirmation every time. Merging this run's
-own PR is an action the run's whole design is about; closing a PR someone else
-opened is not, it destroys their work in progress, and no guard in this tree
-sees it happen. The cheaper gate goes on the action nothing else watches.
+merging is authorised once by the invocation, while closing needs a *per-object*
+confirmation every time. Merging a PR this queue prepared is the action the
+run's whole design is about, and § 1's manifest already binds it to a named
+number and a recorded head; closing a PR someone else opened is neither, it
+destroys their work in progress, and no guard in this tree sees it happen. The
+stricter gate goes on the action nothing else watches.
 
 ## 5. Drive CI green — bounded
 
@@ -240,13 +250,12 @@ After each merge the base has moved, so the next PR is re-synced against the
 NEW base — that is the loop, and it is why pre-greening several PRs ahead of
 their merges is wasted work.
 
-**While the merge step is gated, that loop does not turn**, and the section
-below is written for when it does. Nothing merges, so the base does not
-advance, no PR leaves the open list, and an `all` run is a **preparation
-sweep**: it syncs, classifies, greens and reports each PR once, then stops. It
-does not re-prepare a PR its own predecessor invalidated, because it has no
-predecessor that landed. The cutoff below still bounds it; the window below
-still cannot close it, for the reason § 7 gives.
+**Under `--no-merge` that loop does not turn**, and the paragraph above is
+written for the form that does. Nothing merges, so the base does not advance,
+no PR leaves the open list, and the run is a **preparation sweep**: it syncs,
+classifies, greens and reports each PR once, then stops. It does not re-prepare
+a PR its own predecessor invalidated, because it has no predecessor that
+landed. The cutoff below bounds both forms.
 
 **Cutoff.** When the manifest is exhausted, recompute the open-PR list
 **exactly once**. PRs that appeared during the run are drained as ONE final
@@ -308,10 +317,9 @@ run, and do not proceed to the next PR.
 
 ## 8. Kill switches, and what happens after a merge
 
-**Armed during preparation, not only before a merge** — otherwise every switch
-below is unreachable while the merge step is gated, and a preparation sweep has
-no way to stop at all. Each one aborts the current PR and ends the run on any
-of:
+**Armed during preparation, not only before a merge** — otherwise a
+`--no-merge` sweep would have no way to stop at all. Each one aborts the current
+PR and ends the run on any of:
 
 - target number or head SHA differs from the manifest;
 - the base advanced by an actor other than this run;
@@ -365,9 +373,10 @@ conflict resolution. The disposition set is closed:
 
 ## Rules
 
-- **Never merge while the gate is closed.** Until the `merge-authority`
-  blocker resolves, every invocation stops at mergeable-and-open, `--no-merge`
-  or not. Once it opens, `--no-merge` is still the explicit way to say stop.
+- **Never merge a PR the invocation did not name.** The authorization is the
+  owner's own `/pr:merge` sentence and reaches exactly the manifest § 1
+  snapshotted from it; a PR that arrived afterwards needs its own go-ahead.
+  `--no-merge` is the explicit way to say stop before § 9.
 - **Never widen, patch, or rebuild-around the git guard.** Verification of the
   authorization window is read-only.
 - **Never rebase a pushed branch**; the base is merged in.

package/dist/agent-src/commands/profile/activate.md

@@ -79,4 +79,4 @@ unscoped artefacts are always in `shown`.
 ## See also
 
 - [`/profile show`](show.md) · [`/profile deactivate`](deactivate.md)
-- [`docs/contracts/session-profile-overlay.md`](../../../docs/contracts/session-profile-overlay.md)
+- [`docs/contracts/session-profile-overlay.md`](../../docs/contracts/session-profile-overlay.md)

package/dist/agent-src/commands/profile/show.md

@@ -38,7 +38,7 @@ deterministic template (no LLM), the right content for an employee-facing surfac
 ./scripts-run src/scripts/config/session_profiles show --plain
 ```
 
-Shape + constraints: [`session-profile-overlay` § Plain status surface](../../../../docs/contracts/session-profile-overlay.md#plain-status-surface).
+Shape + constraints: [`session-profile-overlay` § Plain status surface](../../docs/contracts/session-profile-overlay.md#plain-status-surface).
 
 ### 2. Report
 

package/dist/agent-src/commands/research/deep.md

@@ -96,8 +96,8 @@ Read {fields_path} to get all field definitions.
    no part is written unless a retrieved source grounds it. And run at least
    one search that actively tries to **falsify** the leading hypothesis (rule
    alternatives in or out), not only searches that confirm it. Distinct from
-   [`source-discovery-gate`](../../../../src/rules/source-discovery-gate.md)
-   (structural evidence) and [`verify-before-complete`](../../../../src/rules/verify-before-complete.md)
+   [`source-discovery-gate`](../../rules/source-discovery-gate.md)
+   (structural evidence) and [`verify-before-complete`](../../rules/verify-before-complete.md)
    (completion evidence) — this is *research* evidence.
 
 ## Output path

package/dist/agent-src/commands/research/report.md

@@ -59,8 +59,8 @@ Before writing, apply the **per-part grounding + disconfirmation gate**: every
 part of the request must be grounded in a retrieved source before it appears in
 the report, and at least one search must have actively tried to falsify the
 leading hypothesis (not only confirm it). Distinct from
-[`source-discovery-gate`](../../../../src/rules/source-discovery-gate.md) and
-[`verify-before-complete`](../../../../src/rules/verify-before-complete.md).
+[`source-discovery-gate`](../../rules/source-discovery-gate.md) and
+[`verify-before-complete`](../../rules/verify-before-complete.md).
 
 The agent itself reads each JSON + `fields.yaml` + the user's TOC
 choices, then writes `{topic_slug}/report.md`. **No `generate_report.py`