@event4u/agent-config 7.5.0 → 8.1.0

package/dist/agent-src/rules/architecture.md

@@ -8,10 +8,8 @@ triggers:
   - keyword: "service"
   - keyword: "module"
   - intent: "structural decision"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, engineering]
+packs: [meta]
 ---
 
 # Architecture Rules

package/dist/agent-src/rules/artifact-drafting-protocol.md

@@ -2,16 +2,20 @@
 type: "auto"
 tier: "2a"
 alwaysApply: false
-description: "Creating a new skill/rule/command/guideline or significantly rewriting one — runs mandatory Understand → Research → Draft first"
+description: "New or significantly rewritten skill/rule/command/guideline — mandatory Understand → Research → Draft first"
 triggers:
   - intent: "create new skill"
   - intent: "create new rule"
   - intent: "create new command"
   - intent: "create new guideline"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+  - phrase: "new skill"
+  - phrase: "new rule"
+  - phrase: "new command"
+  - phrase: "new guideline"
+  - phrase: "neue Regel"
+  - phrase: "bau mir ein Skill"
+workspaces: [agent-config-maintainer, engineering]
+packs: [meta]
 ---
 
 # Artifact Drafting Protocol
@@ -81,10 +85,35 @@ Enforce size live: *"Body is at 420/500 lines. Split?"* (budgets per
 `size-enforcement`). New skills also get an `evals/triggers.json` stub
 (5 should-trigger + 5 should-not-trigger). See `skill-writing` § 1c.
 
+## Roadmap-run batch mode — the ONE structured bypass
+
+When a `/roadmap:process-*` run starts under an **accepted execution
+contract** ([`roadmap-execution-contract`](../contexts/execution/roadmap-execution-contract.md))
+whose pre-scan detected artifact-authoring steps, the protocol runs in
+batch mode for exactly those artifacts:
+
+- **Phase B (Research) runs ONCE at contract time, against the CURRENT
+  artifact state** — one overlap scan covering every artifact the
+  roadmap plans; results (nearest matches, extend-vs-create verdicts)
+  are surfaced inside the contract summary the user accepts. This is
+  why authoring-time-only checking is not enough: a sibling roadmap may
+  have landed overlapping artifacts between authoring and execution.
+- **Phases A (Understand) and C (Draft) run non-interactively during
+  the run** — the roadmap step text is the Understand input; the
+  contract acceptance is the approval that the per-phase prompts exist
+  to obtain.
+- **Scope is the batch, nothing more.** An artifact NOT declared in the
+  roadmap (discovered mid-run) triggers the full interactive protocol —
+  or, under the contract, the scope-out-of-roadmap halt.
+- Batch mode never skips the Research pass itself — it relocates and
+  batches it. `artifact_protocol: skip` does not exist.
+
 ## Golden rules
 
 - Every phase ends with a numbered-options prompt. No silent progression.
-- Zero autopilot — agent proposes, human decides.
+- Zero autopilot — agent proposes, human decides. (In roadmap-run batch
+  mode the human decision is the contract acceptance; the per-phase
+  prompts are pre-satisfied for the declared batch.)
 - At most two propose → reject cycles; then stop.
 - Commit only on approval.
 - Bypass is legitimate — *"just write it"* drops the protocol immediately.

package/dist/agent-src/rules/artifact-engagement-recording.md

@@ -11,10 +11,8 @@ routes_to:
   - "contract:artifact-engagement-flow"
 load_context:
   - "../contexts/contracts/artifact-engagement-flow.md"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, engineering]
+packs: [meta]
 ---
 
 <!-- cloud_safe: noop -->

package/dist/agent-src/rules/ask-when-uncertain.md

@@ -3,10 +3,8 @@ type: "always"
 tier: "3"
 description: "Ask when uncertain — don't guess, assume, or improvise"
 alwaysApply: true
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
+packs: [meta]
 ---
 
 # Ask When Uncertain
@@ -24,17 +22,15 @@ Even if trivial or independent — exactly one.
 
 ## When to ask
 
-- Requirement ambiguous or multi-interpretable.
+- Requirement ambiguous / multi-interpretable.
 - Not 100 % sure which approach is correct.
-- About to touch code you haven't fully understood.
-- Choosing between multiple valid approaches.
+- Touching code you haven't fully understood.
+- Multiple valid approaches.
 - A fix "seems to work" but you can't explain why.
 
 ## Vague-request triggers — MUST ask
 
-Nine patterns — "improve / optimize" · "add caching" · "make it better / cleaner" · "clean up this file" · "fix this" (no symptom) · "refactor X" · "use best practices" · "handle errors properly" · "add a UI / component / tile / page" in a mixed-framework repo. Match without further context → ask **before** touching code.
-
-Per-pattern missing-info and clarifying questions: [`asking-and-brevity-examples`](../docs/guidelines/agent-infra/asking-and-brevity-examples.md).
+Nine patterns — "improve / optimize" · "add caching" · "make it better / cleaner" · "clean up this file" · "fix this" (no symptom) · "refactor X" · "use best practices" · "handle errors properly" · "add a UI / component / tile / page" in a mixed-framework repo. Match without context → ask **before** touching code. Per-pattern questions: [`asking-and-brevity-examples`](../docs/guidelines/agent-infra/asking-and-brevity-examples.md).
 
 **Escape hatch:** unambiguous from ticket / open file / prior turn → proceed, state the assumption.
 
@@ -48,18 +44,18 @@ Numbered options (per [`user-interaction`](user-interaction.md)). Short.
 2. Two or more separate numbered-option blocks?
 3. User would need a structured reply (`1a, 2b`) instead of a single number?
 
-Any "yes" → **collapse to ONE question**. Hold the rest for their own turn. Rationale: [`asking-and-brevity-examples`](../docs/guidelines/agent-infra/asking-and-brevity-examples.md).
+Any "yes" → **collapse to ONE question**; hold the rest for their own turn.
 
 ### Ordering & handoff
 
-- **Session handoff** — ask LAST, after domain / clarifying questions. Full: [`agent-interaction-and-decision-quality`](../docs/guidelines/agent-infra/agent-interaction-and-decision-quality.md).
+- **Session handoff** — ask LAST, after domain questions ([`agent-interaction-and-decision-quality`](../docs/guidelines/agent-infra/agent-interaction-and-decision-quality.md)).
 - **Model switch** — [`model-recommendation`](model-recommendation.md) STOP-AND-WAIT gate is standalone.
-- **Blocking clarification** — ask FIRST, alone, before research / planning output.
+- **Blocking clarification** — ask FIRST, alone.
 - **Optional refinement** — don't ask; state the assumption, proceed.
 
 ## Impact-based routing (AI Council)
 
-AI Council enabled → questions classified and routed per `decision_resolution`. **Iron Law: `high_impact` and `user_required` ALWAYS reach the user.** Contract: [`ai-council-config`](../docs/contracts/ai-council-config.md).
+Council enabled → questions route per `decision_resolution`. **Iron Law: `high_impact` and `user_required` ALWAYS reach the user** ([`ai-council-config`](../docs/contracts/ai-council-config.md)).
 
 ## Creating new agent artifacts
 

package/dist/agent-src/rules/augment-edit-discipline.md

@@ -15,10 +15,8 @@ validator_ignore:
   - type: "substring"
     pattern: ".agent-src.uncondensed/"
     reason: "Rule scopes the portability gate to the uncondensed authoring tree."
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer]
+packs: [meta]
 ---
 
 # Augment Edit Discipline
@@ -28,4 +26,4 @@ packs:
 **Iron Law (sync).** On any add / rename / delete of skill / rule / command / guideline, update counts and cross-references in the same edit.
 
 Portability body migrated to `guideline:augment-portability-patterns`. Sync body migrated to `skill:agent-docs-writing` (per P4 of `road-to-kernel-and-router.md`).
-Trigger-set above activates both routes under the `balanced` and `full` profiles.
+Trigger-set above activates both routes on demand, independent of the discipline profile (ADR-110).

package/dist/agent-src/rules/autonomous-execution.md

@@ -1,7 +1,7 @@
 ---
 type: "auto"
 tier: "3"
-description: "Whether to ask or act on a workflow step — trivial-vs-blocking, autonomy opt-in, commit default; Hard Floor non-destructive-by-default"
+description: "Ask-or-act on a workflow step — trivial-vs-blocking, autonomy opt-in, commit default; Hard Floor stays"
 alwaysApply: false
 load_context:
   - ../contexts/execution/autonomy-detection.md
@@ -11,10 +11,8 @@ triggers:
   - intent: "trivial workflow question"
   - intent: "autonomy mode"
   - keyword: "personal.autonomy"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
+packs: [meta]
 ---
 
 # Autonomous Execution

package/dist/agent-src/rules/brand-consistency.md

@@ -1,7 +1,7 @@
 ---
 type: "auto"
 tier: "2a"
-description: "Generated UI, copy, and assets are checked against the active brand tokens and voice profile — a value not traceable to a brand token or voice rule is flagged off-brand."
+description: "Generated UI/copy/assets check against active brand tokens + voice profile — untraceable values are flagged off-brand"
 triggers:
   - keyword: "brand"
   - keyword: "on-brand"
@@ -14,10 +14,8 @@ applies_to_user_types:
   - "creator"
   - "developer"
   - "maintainer"
-workspaces:
-  - engineering
-packs:
-  - brand
+workspaces: [engineering]
+packs: [brand]
 ---
 
 # Brand Consistency

package/dist/agent-src/rules/brand-source-of-truth.md

@@ -1,7 +1,7 @@
 ---
 type: "auto"
 tier: "2a"
-description: "The consumer's brand tokens and voice profile are the run's source of truth — the curated brand corpus only fills gaps, never overrides a registered brand value."
+description: "Consumer brand tokens + voice profile are the run's source of truth — the corpus fills gaps, never overrides"
 triggers:
   - keyword: "brand tokens"
   - keyword: "brand voice"
@@ -12,10 +12,8 @@ applies_to_user_types:
   - "creator"
   - "developer"
   - "maintainer"
-workspaces:
-  - engineering
-packs:
-  - brand
+workspaces: [engineering]
+packs: [brand]
 ---
 
 # Brand Source of Truth

package/dist/agent-src/rules/cli-output-handling.md

@@ -1,7 +1,7 @@
 ---
 type: "auto"
 tier: "2a"
-description: "Running verbose CLI output — git, tests, linters, docker, build tools, artisan, npm, composer. Wrap with rtk; tail/grep fallback"
+description: "Verbose CLI output (git, tests, linters, docker, npm, composer) — wrap with rtk; tail/grep fallback"
 triggers:
   - keyword: "git"
   - keyword: "phpstan"
@@ -28,10 +28,8 @@ triggers:
   - phrase: "go build"
 routes_to:
   - "skill:rtk-output-filtering"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, engineering]
+packs: [meta]
 ---
 
 # Cli Output Handling
@@ -39,4 +37,4 @@ packs:
 **Iron Law.** Wrap verbose CLI output with `rtk` when installed; fall back to `tail`/`grep` only when missing.
 
 Body migrated to `skill:rtk-output-filtering` (per P4 of `road-to-kernel-and-router.md`).
-Trigger-set above activates this routing under the `balanced` and `full` profiles.
+Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).

package/dist/agent-src/rules/command-suggestion-policy.md

@@ -1,7 +1,7 @@
 ---
 type: "auto"
 tier: "mechanical-already"
-description: "Prompt without /command matching an eligible slash command — surface matches as numbered options with as-is escape; never auto-executes"
+description: "Prompt matches an eligible slash command — surface as numbered options with as-is escape; never auto-execute"
 triggers:
   - phrase: "free-form prompt"
   - phrase: "command suggestion"
@@ -9,10 +9,8 @@ routes_to:
   - "contract:command-suggestion-flow"
 load_context:
   - "../contexts/contracts/command-suggestion-flow.md"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
+packs: [meta]
 ---
 
 # Command Suggestion Policy

package/dist/agent-src/rules/commit-conventions.md

@@ -8,10 +8,8 @@ triggers:
   - phrase: "conventional commits"
 routes_to:
   - "skill:conventional-commits-writing"
-workspaces:
-  - engineering
-packs:
-  - engineering-base
+workspaces: [engineering]
+packs: [engineering-base]
 ---
 
 # Commit Conventions
@@ -19,4 +17,4 @@ packs:
 **Iron Law.** Use Conventional Commits (`feat:`, `fix:`, `chore:` …); branches `<type>/<short-slug>`; never invent your own format. Subjects + branch names stay emoji-free per [`no-decorative-emojis-in-git-surfaces`](no-decorative-emojis-in-git-surfaces.md); body emojis allowed only with an in-artifact legend.
 
 Body migrated to `skill:conventional-commits-writing` (per P4 of `road-to-kernel-and-router.md`).
-Trigger-set above activates this routing under the `balanced` and `full` profiles.
+Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).

package/dist/agent-src/rules/commit-policy.md

@@ -5,10 +5,8 @@ description: "Commit policy — never commit and never ask about committing unle
 alwaysApply: true
 load_context:
   - ../contexts/authority/commit-mechanics.md
-workspaces:
-  - engineering
-packs:
-  - engineering-base
+workspaces: [engineering]
+packs: [engineering-base]
 ---
 
 # Commit Policy
@@ -20,22 +18,32 @@ NEVER COMMIT. NEVER ASK ABOUT COMMITTING.
 EXCEPTIONS ARE EXPLICIT, NOT INFERRED.
 ```
 
-Applies regardless of `personal.autonomy`, conversation momentum, or "clean stopping point". Default: **no commit, no question**.
+Holds regardless of `personal.autonomy`, momentum, or "clean stopping point". Default: **no commit, no question**.
 
 ## Exceptions — when committing IS allowed
 
 Exactly four:
 
-1. **User says so this turn** — "commit this now", "go ahead and commit". This commit only, not standing.
-2. **Standing instruction not yet revoked** — "commit after every phase" earlier in the conversation; cache and honor.
-3. **Commit command invoked** — `/commit` (with confirmation) or `/commit:in-chunks` (auto-split, no confirmation).
-4. **Roadmap authorization** — roadmap file lists explicit commit steps and the user invoked roadmap execution.
+1. **User says so this turn** — "commit this now". This commit only, not standing.
+2. **Standing instruction not yet revoked** — "commit after every phase"; cache and honor.
+3. **Commit command invoked** — `/commit` (confirmed) or `/commit:in-chunks` (auto-split).
+4. **Roadmap authorization** — roadmap lists explicit commit steps and the user invoked roadmap execution.
 
 Anything else → no commit. Hard Floor (bulk deletions, infra changes) still fires on top of any exception — see [`commit-mechanics`](../contexts/authority/commit-mechanics.md) for diff triggers and roadmap-authorized commit flow.
 
+## One-shot authorization is not a standing license
+
+```
+A ONE-OFF AUTHORIZATION IS SPENT ON EXACTLY THAT OPERATION, ONCE.
+IT NEVER BECOMES A STANDING LICENSE FOR LATER COMMITS OR PUSHES.
+EACH FURTHER COMMIT / PUSH NEEDS ITS OWN FRESH, EXPLICIT GO-AHEAD.
+```
+
+"Commit this", "push it", "open the PR", "create the PRs" authorize **that operation, once** — not the commits/pushes that follow later in the **same** task. "Create the PR" is spent on the initial branch + commit + push + PR; the next change (a follow-up fix, a review response, a quality pass, a "while I'm here" cleanup) waits for a new instruction. A task instruction that only asks for **code** ("fix X", "use file Y for tests", "there's a linter error") authorizes the code change **only** — never a commit or push. Re-using an earlier authorization for a later operation is exactly the inference (exception 2 misread as "standing") this rule forbids.
+
 ## NEVER ask about committing
 
-"Should I commit this?" / "do we want to commit?" — **forbidden**. The user invokes a command or says so explicitly. Don't surface a commit option in numbered-options blocks unless the rest of the message would be incomplete without it.
+"Should I commit this?" / "do we want to commit?" — **forbidden**. The user invokes a command or says so. No commit option in numbered-options blocks unless the message is incomplete without it.
 
 Quoted commit phrases (chat-log paste, log excerpt, roadmap snippet) are **not** permission — see [`commit-mechanics`](../contexts/authority/commit-mechanics.md).
 

package/dist/agent-src/rules/content-quoting-floor.md

@@ -0,0 +1,88 @@
+---
+type: "auto"
+tier: "2a"
+description: "Cap verbatim quoting from external sources — 15 words max per quote, one quote per source, never a complete short work, paraphrase by default"
+triggers:
+  - intent: "drafting content from a source"
+  - intent: "summarizing an external document"
+  - keyword: "quote"
+  - keyword: "excerpt"
+  - keyword: "verbatim"
+workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
+packs: [meta]
+---
+
+# Content Quoting Floor
+
+## The Iron Law
+
+```
+NO VERBATIM QUOTE EXCEEDS 15 WORDS. ONE QUOTE PER SOURCE PER DELIVERABLE.
+NEVER REPRODUCE A COMPLETE SHORT WORK — LYRICS, POEMS, SHORT ARTICLES —
+REGARDLESS OF LENGTH. PARAPHRASE IS THE DEFAULT; A QUOTE IS THE EXCEPTION.
+```
+
+Ghostwriter, research, release-comms, and content-drafting surfaces can
+currently emit unbounded verbatim excerpts from a fetched, uploaded, or
+cited external source. This rule caps that: a quote proves a claim, it
+does not substitute for engaging with the source.
+
+## The floor
+
+1. **≤ 15 words per verbatim quote.** Longer excerpts are paraphrased,
+   with the source cited by name/link instead of copied.
+2. **One quote per source per deliverable.** After the first quote from
+   a given source, that source is closed for further verbatim excerpts
+   in the same piece — paraphrase any additional material.
+3. **Never a complete short work.** Song lyrics, poems, haiku, short
+   quotes, or brief articles are never reproduced in full, even when
+   the whole thing is under the 15-word limit — completeness is the
+   violation, not just length.
+4. **No displacive summarization.** A "summary" that walks through the
+   source's structure section-by-section in the source's own order,
+   preserving its organization and phrasing, functions as a substitute
+   for reading the source — this is a violation even without literal
+   quoting. Summaries restructure and compress; they do not mirror.
+5. **Paraphrase by default.** Reach for a quote only when the exact
+   wording itself is the point (a legal term, a precise technical
+   claim, a direct attribution the user needs verbatim) — not as the
+   default mode of engaging with source material.
+
+## Carve-outs
+
+- **User-owned or user-supplied text.** Content the user wrote, pasted,
+  or explicitly authorized for verbatim use is not "an external
+  source" under this rule — it's the user's own material.
+- **License-permitted vendored content.** Code or text vendored under a
+  license that requires or permits verbatim inclusion (Apache/MIT
+  attribution blocks, etc.) — see [`source-confidentiality`](source-confidentiality.md)
+  for the attribution rules that govern that carve-out.
+- **Code snippets.** This rule governs prose quoting from written
+  sources (articles, documents, transcripts) — it does not limit
+  quoting source code, which has its own citation norms.
+
+## Failure modes
+
+- Pasting a multi-paragraph block from a fetched article "for context"
+  instead of paraphrasing it.
+- Quoting the same source three times across one deliverable because
+  each quote "proves a different point" — one quote closes the source.
+- Reproducing a full haiku or a four-line lyric snippet because it's
+  "short enough" — completeness, not length, is what this rule bans.
+- A "summary" that is actually the source's own outline with lighter
+  wording — the displacive-summarization violation.
+
+## See also
+
+- [`domain-safety-disclaimer`](domain-safety-disclaimer.md) — the
+  advisory-disclaimer floor this rule complements; overlap checked,
+  no duplication (that rule governs disclaimers, not quote length).
+- [`untrusted-input-defense`](untrusted-input-defense.md) — governs
+  treating fetched content as data vs instructions; this rule governs
+  how much of that data may be reproduced verbatim once it IS being
+  used as source material.
+- [`docs/contracts/write-engine.md`](../docs/contracts/write-engine.md) —
+  ghostwriter's disclosure-footer contract; this rule's quote floor
+  applies to any ghostwriter draft that cites an external source.
+- [`source-confidentiality`](source-confidentiality.md) — the license-
+  required-attribution carve-out for vendored code/text.

package/dist/agent-src/rules/context-hygiene.md

@@ -8,10 +8,8 @@ triggers:
   - intent: "tool loop"
   - intent: "fresh chat"
   - keyword: "3-failure"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
+packs: [meta]
 ---
 
 # Context Hygiene
@@ -154,7 +152,7 @@ manually so the dashboard or another tool can read the latest
 counters, run:
 
 ```bash
-python3 scripts/context_hygiene_hook.py < /dev/null
+./scripts-run src/scripts/context_hygiene_hook < /dev/null
 ```
 
 The script reads from stdin if a JSON envelope is provided and

package/dist/agent-src/rules/copilot-routing.md

@@ -1,17 +1,15 @@
 ---
 type: "auto"
 tier: "3"
-description: "Configuring GitHub Copilot — copilot-instructions.md, PR-review patterns, suggestion behavior — route to copilot-config"
+description: "Configuring GitHub Copilot (copilot-instructions.md, PR-review patterns) — route to copilot-config"
 triggers:
   - keyword: "copilot"
   - phrase: "copilot-instructions"
   - phrase: "copilot pr review"
 routes_to:
   - "skill:copilot-config"
-workspaces:
-  - agent-config-maintainer
-packs:
-  - meta
+workspaces: [agent-config-maintainer, engineering]
+packs: [meta]
 ---
 
 # Copilot Routing
@@ -19,4 +17,4 @@ packs:
 **Iron Law.** Tuning the GitHub Copilot AI assistant itself (instructions, PR-review patterns, suggestion behavior) → load the `copilot-config` skill, not `devcontainer` (which covers the dev environment Copilot runs inside).
 
 Body migrated to `skill:copilot-config`. Disambiguates the copilot-config ↔ devcontainer cluster head per [`adr-architectural-consensus-mechanism`](../docs/contracts/adr-architectural-consensus-mechanism.md).
-Trigger-set above activates this routing under the `balanced` and `full` profiles.
+Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).

package/dist/agent-src/rules/decision-revisit-gate.md

@@ -0,0 +1,120 @@
+---
+type: "auto"
+tier: "2b"
+description: "A beneficial change blocked by a past lock (honest-null, don't-relitigate memory, budget canon, ADR) must be surfaced with a council re-evaluation offer, never silently dropped"
+alwaysApply: false
+council_depth: deep
+triggers:
+  - intent: "blocked by prior decision"
+  - intent: "revisit past verdict"
+  - keyword: "don't relitigate"
+  - keyword: "honest null"
+  - keyword: "already decided"
+  - keyword: "locked decision"
+  - keyword: "budget blocks"
+workspaces: [agent-config-maintainer, engineering]
+packs: [meta]
+---
+
+# Decision Revisit Gate
+
+## The Iron Law
+
+```
+A LOCK IS A DECISION UNDER PAST CONDITIONS, NOT A PERMANENT LAW.
+BENEFIT BLOCKED BY A LOCK → SURFACE + OFFER RE-EVALUATION.
+NEVER SILENT COMPLIANCE. NEVER SILENT DROP OF A GOOD CHANGE.
+```
+
+An agent that finds a genuinely beneficial change blocked by a recorded
+past decision — an honest-null eval verdict, a "don't relitigate"
+memory or context note, a token-frugality/budget canon line, or an ADR —
+does not quietly comply and drop the change. It surfaces the conflict
+and offers the user a path to re-evaluate the lock. Progress means
+adaptation: locks encode what was true when they were written, not a
+ceiling on what the package may ever become.
+
+## What counts as a "lock"
+
+- An eval verdict recorded as an honest null (a mechanism was tested,
+  showed no lift, and the disposition says "don't rebuild without new
+  evidence").
+- A memory entry or `agents/settings/contexts/` note tagged "don't
+  relitigate" / "settled" / a locked council convergence.
+- A budget or frugality-canon line (`token-budget-discipline`,
+  `telegraph-speak`, thin-projector trimming) that rejects a change on
+  cost grounds alone.
+- An ADR whose decision is being cited as a blocker for the current change.
+
+## What to do when it fires
+
+1. **Mechanism-match check — do this FIRST.** A verdict settles the
+   *mechanism it tested*, not every future proposal that resembles it.
+   Before applying the lock, verify the blocked change is actually the
+   same mechanism — not merely a similar-sounding one. A null on
+   hardened blocking enforcement does not automatically cover
+   discretionary contextual nudges; a null on one architecture does not
+   cover a materially different one. If the mechanism differs, the lock
+   does not apply — proceed, noting the distinction.
+2. **If the mechanism genuinely matches**, do not silently comply.
+   Surface, in one short block:
+   - What change is blocked.
+   - Which lock blocks it (cite the memory/context/ADR).
+   - Under what conditions the lock was recorded (date, evidence, or
+     "maintainer decision" if settled-by-decision rather than
+     settled-by-evidence).
+   - What has changed since (new evidence, new model generation, new
+     tooling, repeated encounters) that makes revisiting worth the cost.
+3. **Offer numbered options** (per [`user-interaction`](user-interaction.md)),
+   always including: re-evaluate the lock in the AI council. Other
+   options: keep the lock as-is, or proceed without the blocked change.
+4. **On re-evaluation:** route to [`decision-review`](../skills/decision-review/SKILL.md)
+   for the backward-audit procedure and to [`ai-council`](../skills/ai-council/SKILL.md)
+   for the debate mechanics. This rule owns the obligation to surface;
+   those skills own the procedure.
+5. **Record the outcome** with scope + `revisit-if` per
+   [`ai-council`](../skills/ai-council/SKILL.md)'s convergence-summary
+   contract — every re-evaluated lock gets a fresh, correctly-scoped
+   disposition, not a re-statement of the old one.
+
+## When NOT to fire
+
+- The blocked change has no real benefit — this rule is not a lever to
+  reopen every settled question; [`no-cheap-questions`](no-cheap-questions.md)
+  still governs whether the resulting numbered-options block is a real
+  question or noise. A revisit-offer with a genuine trade-off is never
+  a "cheap question" under that rule — but a revisit-offer with no
+  actual case for change is.
+- The mechanism-match check (step 1) shows the lock is the same
+  mechanism and no new evidence exists — apply the lock, no surfacing
+  needed; this is the lock working as intended.
+- The user already declined a revisit on this exact lock this
+  conversation — per [`scope-control § Decline = silence`](scope-control.md),
+  do not re-ask.
+
+## Failure modes
+
+- Treating a "don't relitigate" memory as permanently closed instead of
+  as settled-under-conditions-X.
+- Applying a null verdict to a superficially similar but architecturally
+  different mechanism without running the mechanism-match check.
+- Letting the token-frugality canon auto-reject a net-positive change
+  without surfacing the trade-off — see [`token-budget-discipline`](token-budget-discipline.md)'s
+  value-over-budget clause.
+- Silently dropping a good idea because "we already decided this" —
+  the canonical failure this rule exists to stop.
+
+## See also
+
+- [`decision-review`](../skills/decision-review/SKILL.md) — the backward-audit
+  procedure this rule routes to when a lock is genuinely re-evaluated.
+- [`ai-council`](../skills/ai-council/SKILL.md) — the re-evaluation mechanism;
+  owns the convergence-summary scope + `revisit-if` contract.
+- [`decision-record`](../skills/decision-record/SKILL.md) — forward-flow decision
+  locking; the escalation litmus there names the reopening condition up front.
+- [`token-budget-discipline`](token-budget-discipline.md) — the frugality-canon
+  value-over-budget escalation this rule's budget-lock case defers to.
+- [`no-cheap-questions`](no-cheap-questions.md) — the question-quality floor a
+  revisit-offer must still clear.
+- [`ask-when-uncertain`](ask-when-uncertain.md) — the numbered-options shape
+  used to present the revisit offer.