@event4u/agent-config 9.26.0 → 9.28.0

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

@@ -11,6 +11,8 @@ routes_to:
   - "skill:devcontainer"
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 20
+obligation_frequency: "none"
 ---
 
 # Devcontainer Routing

package/dist/agent-src/rules/doc-screenshot-hygiene.md

@@ -27,6 +27,8 @@ workspaces: [agent-config-maintainer, construction, engineering, finance, founde
 packs: [meta]
 collision_ok:
   "screenshot": "a screenshot shipping into docs is the PII/anonymization gate"
+# obligation: line 49
+obligation_frequency: "per-event"
 ---
 
 # Doc-Screenshot Hygiene

package/dist/agent-src/rules/docker-commands.md

@@ -15,6 +15,8 @@ collision_ok:
   "artisan": "artisan runs inside the project container, never on the host"
   "composer": "composer runs inside the project container"
   "docker": "its own core subject"
+# obligation: line 22
+obligation_frequency: "per-edit"
 ---
 
 # Docker Commands

package/dist/agent-src/rules/domain-adoption-policy.md

@@ -18,6 +18,8 @@ workspaces: [agent-config-maintainer]
 packs: [meta]
 collision_ok:
   "src/skills/": "a skill in a fresh vertical is exactly the domain-gate surface"
+# obligation: line 38
+obligation_frequency: "per-task"
 ---
 
 # Domain Adoption Policy

package/dist/agent-src/rules/domain-safety-disclaimer.md

@@ -42,6 +42,8 @@ workspaces: [agent-config-maintainer, construction, engineering, finance, founde
 packs: [meta]
 collision_ok:
   "review this contract": "contract review is advisory-shaped — the not-legal-advice footer floor"
+# obligation: line 52
+obligation_frequency: "per-task"
 ---
 
 # Domain Safety — Advisory Disclaimer

package/dist/agent-src/rules/domain-safety-pii.md

@@ -42,6 +42,8 @@ applies_to_user_types:
   - "all"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 52
+obligation_frequency: "per-task"
 ---
 
 # Domain Safety — PII Redaction

package/dist/agent-src/rules/domain-safety-retention.md

@@ -27,6 +27,8 @@ applies_to_user_types:
   - "gtm"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 47
+obligation_frequency: "per-turn"
 ---
 
 # Domain Safety — Data Retention

package/dist/agent-src/rules/downstream-changes.md

@@ -11,6 +11,8 @@ triggers:
 self_contained: true
 workspaces: [engineering]
 packs: [engineering-base]
+# obligation: line 30
+obligation_frequency: "per-edit"
 ---
 
 # Downstream Changes

package/dist/agent-src/rules/engineering-safety-floor.md

@@ -28,6 +28,8 @@ workspaces: [engineering]
 packs: [engineering-base]
 collision_ok:
   "migration": "a prod migration is a hard-floor evidence surface (rollback path, blast radius)"
+# obligation: line 49
+obligation_frequency: "per-commit"
 ---
 
 # Engineering Safety Floor

package/dist/agent-src/rules/evaluator-independence.md

@@ -20,6 +20,12 @@ enforced_by:
   - "hook:evidence-independence"
 collision_ok:
   "honest null": "this rule asks how a recorded null was PRODUCED; decision-revisit-gate asks whether it may be REVISITED — different decision points on the same artefact"
+# obligation: dispatching an evaluator is a tool call, and the guard is a pre_tool_use
+# concern that reads that prompt — src/rules/evaluator-independence.md:81
+obligation_frequency: "per-edit"
+# frequency-override: line 70 states a per-turn clause ("one evaluation per turn"),
+# but the guard counts it AT the dispatch, which is a tool call — a per-edit point
+# carrier sees every dispatch, so it carries the per-turn cap too.
 ---
 
 # Evaluator Independence
@@ -85,11 +91,16 @@ pre-loaded verdict, and **blocks** a second *self-scoped* evaluation dispatch in
 the same turn; it **warns** on the first. It reads the prompt the agent is about
 to send, so items 1 and 4 above are mechanically enforced.
 
-Two limits, stated because round 2 measured them. The pre-loaded-verdict list is
+Three limits, stated because they were measured. The pre-loaded-verdict list is
 a **phrase list**, so a paraphrase evades it — it catches recurrences of known
-steering wording, not steering as such. And the turn boundary is the
+steering wording, not steering as such. The turn boundary is the
 authorization ledger's `detected_at` stamp, because the envelope carries no turn
-id; with no ledger yet, the counter falls back to session scope.
+id; with no ledger yet, the counter falls back to session scope. And the slot
+itself is not universal: `pre_tool_use` exists on **three** hosts — augment,
+claude, cowork. On cursor, cline, windsurf, gemini and copilot this guard has
+nowhere to bind, so items 1 and 4 join 2 and 3 as model-carried there. The
+frequency join in `check_enforcement_coverage.ts` reports exactly that set, and
+`agent-config hooks:status` answers it for the host you are on right now.
 
 Items 2 and 3 — an honestly chosen scope, and recording the prompt with the
 verdict — are **not** enforced by anything. A narrowed scope is not decidable

package/dist/agent-src/rules/external-code-graph-interop.md

@@ -17,6 +17,8 @@ applies_to_user_types:
 self_contained: true
 workspaces: [engineering]
 packs: [meta]
+# obligation: line 37
+obligation_frequency: "per-turn"
 ---
 
 # External Code-Graph Interop
@@ -68,7 +70,8 @@ AND the repo contains a detectable index:
   routing skill: `agent-config code-graph detect|query|affected|path` over the
   native engine or a consumer-shipped index, grep as the stated fallback. On
   hook-capable hosts the PreToolUse `code-graph` nudge surfaces this once per
-  session; on instruction-file hosts this rule is the surface.
+  session; on instruction-file hosts this rule is the surface. Which of the two
+  you are on is `agent-config hooks:status`, not a guess from the host name.
 - [`discovery_graph`](../scripts/discovery_graph.ts) — this suite's OWN artefact
   relation-graph (`affected`/`explain`); the external code-graph is the
   *source-code* analogue this rule defers to for code questions.

package/dist/agent-src/rules/external-reference-deep-dive.md

@@ -10,6 +10,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 20
+obligation_frequency: "per-task"
 ---
 
 # external-reference-deep-dive

package/dist/agent-src/rules/fast-path-marker-visibility.md

@@ -14,6 +14,8 @@ validator_ignore:
 self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 30
+obligation_frequency: "per-turn"
 ---
 
 # Fast-Path Marker Visibility

package/dist/agent-src/rules/finance-safety-floor.md

@@ -33,13 +33,15 @@ packs: [finance-basic, finance-advanced]
 trust:
   level: advisory
   human_review_required: true
+# obligation: line 53
+obligation_frequency: "per-task"
 ---
 <!-- agent-config:human-review-banner -->
 > HUMAN REVIEW REQUIRED · trust: advisory · owner: unknown
 
 # Finance Safety Floor
 
-Domain safety floor for finance-pack artefacts (cash, runway, valuation, scenario, unit economics, forecasting). Auto-activates when `pack-finance-basic` or `pack-finance-advanced` is installed.
+Domain safety floor for finance-pack artefacts (cash, runway, valuation, scenario, unit economics, forecasting). Auto-activates when `pack-finance-basic` or `pack-finance-advanced` is installed — `agent-config packs:active` says whether it is, and names the degraded case where zero packs load and this floor cannot activate at all.
 
 ## Iron Law — no final investment recommendation
 

package/dist/agent-src/rules/framework-neutrality-in-generic-skills.md

@@ -43,6 +43,8 @@ collision_ok:
   "formrequest": "FormRequest named in a generic artifact is leakage — the lint surface"
   "phpstan": "phpstan named in a generic artifact is leakage — the lint surface"
   "rector": "rector named in a generic artifact is leakage — the lint surface"
+# obligation: line 65
+obligation_frequency: "per-edit"
 ---
 
 # framework-neutrality-in-generic-skills

package/dist/agent-src/rules/git-history-discipline.md

@@ -23,6 +23,8 @@ workspaces: [engineering]
 packs: [engineering-base]
 enforced_by:
   - "hook:block-no-verify"
+# obligation: line 35
+obligation_frequency: "per-commit"
 ---
 
 # Git History Discipline
@@ -82,4 +84,4 @@ Trigger-set above activates this routing on demand, independent of the disciplin
 - [`commit-policy`](commit-policy.md) — commits are the user's call; rewriting them is a stronger version of the same restriction.
 - [`token-efficiency`](token-efficiency.md) — Iron Law on burning the user's tokens for cosmetic gain.
 - [`skill:git-workflow`](../skills/git-workflow/SKILL.md) — Safe Squash-After-Push protocol and Divergent-State Recovery decision tree.
-- `git … --no-verify` / `core.hooksPath` overrides — deterministically blocked by the `block-no-verify` PreToolUse guard (`src/scripts/hooks/block_no_verify.ts`, registered in `hook_manifest.yaml`).
+- `git … --no-verify` / `core.hooksPath` overrides — deterministically blocked by the `block-no-verify` PreToolUse guard (`src/scripts/hooks/block_no_verify.ts`, registered in `hook_manifest.yaml`) **on the three hosts that have a `pre_tool_use` slot at all** — augment, claude, cowork. On cursor, cline, windsurf, gemini and copilot the guard has nowhere to bind, so on those hosts the Iron Laws above are model-carried and "deterministically blocked" is not a claim this rule can make. Surfaced by the frequency join in `check_enforcement_coverage.ts`, which reports the per-commit obligation as uncovered on exactly those platforms. To check the host you are on rather than trusting this sentence, run `agent-config hooks:status`.

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

@@ -9,6 +9,8 @@ triggers:
   - keyword: "convention"
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 16
+obligation_frequency: "per-edit"
 ---
 
 # Guidelines

package/dist/agent-src/rules/history-discipline.md

@@ -19,12 +19,16 @@ workspaces: [engineering]
 packs: [history-discipline]
 trust:
   level: professional
+# obligation: line 35
+obligation_frequency: "per-edit"
 ---
 
 # History Discipline
 
 Pack floor for the `history-discipline` pack (default-off; auto-activates
-when the pack is installed). Agents get history wrong in both directions:
+when the pack is installed — `agent-config packs:active` says whether it is,
+and names the degraded case where zero packs load and this floor cannot
+activate at all). Agents get history wrong in both directions:
 missing entirely on data that needs it, or over-built as event sourcing
 where a row-level log suffices — and audit tables that themselves grow
 without bound.

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

@@ -16,6 +16,8 @@ applies_to_user_types:
 self_contained: true
 workspaces: [engineering]
 packs: [frontend-design]
+# obligation: line 41
+obligation_frequency: "per-edit"
 ---
 
 # Icon Consistency

package/dist/agent-src/rules/image-likeness-and-rights.md

@@ -22,6 +22,8 @@ collision_ok:
   "/image:": "rights/likeness gate on the image-generation surface"
   "likeness": "its own core subject — the rights gate"
   "scripts/ai-image/adapters/": "adapter edits touch the likeness-gated generation path"
+# obligation: line 32
+obligation_frequency: "per-event"
 ---
 
 # Image Likeness and Rights

package/dist/agent-src/rules/improve-before-implement.md

@@ -20,6 +20,8 @@ collision_ok:
   "migration": "a migration is a significant behavioural change — the pre-implementation checks apply"
   "refactor": "refactor = significant change; the demand gate + three checks apply"
   "implement": "its own core trigger — pre-implementation validation"
+# obligation: line 45
+obligation_frequency: "per-task"
 ---
 
 # Improve Before Implement

package/dist/agent-src/rules/invite-challenge.md

@@ -12,6 +12,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 62
+obligation_frequency: "per-task"
 ---
 
 # invite-challenge

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

@@ -20,6 +20,8 @@ collision_ok:
   "artisan": "artisan is a Laravel-flavoured PHP routing cue — load the laravel skill"
   "eloquent": "eloquent is a Laravel routing cue"
   "formrequest": "FormRequest is a Laravel routing cue"
+# obligation: line 29
+obligation_frequency: "none"
 ---
 
 # Laravel Routing

package/dist/agent-src/rules/laravel-translations.md

@@ -16,6 +16,8 @@ trust:
 install:
   default: false
   removable: true
+# obligation: line 23
+obligation_frequency: "per-edit"
 ---
 
 # Laravel Translations

package/dist/agent-src/rules/legal-safety-floor.md

@@ -31,13 +31,15 @@ trust:
 collision_ok:
   "controller": "'controller' is a GDPR role term (controller/processor) in the legal pack"
   "review this contract": "the legal-pack contract-review gate — both floors must fire"
+# obligation: line 103
+obligation_frequency: "per-task"
 ---
 <!-- agent-config:human-review-banner -->
 > HUMAN REVIEW REQUIRED · trust: advisory · owner: unknown
 
 # Legal Safety Floor
 
-Domain safety floor for the `legal-review-prep` pack (contract/NDA/DPA review, legal triage). Auto-activates when `pack-legal-review-prep` is installed. Sibling to `finance-safety-floor` / `strategy-safety-floor`. Every output is a **draft to PREPARE for attorney review**, never legal advice. Operating mechanics migrated to [`legal-practice-profile § Legal safety floor`](../skills/legal-practice-profile/SKILL.md) (per P4 of `road-to-kernel-and-router`) — the Iron Laws below stay here.
+Domain safety floor for the `legal-review-prep` pack (contract/NDA/DPA review, legal triage). Auto-activates when `pack-legal-review-prep` is installed — `agent-config packs:active` says whether it is, and names the degraded case where zero packs load and this floor cannot activate at all. Sibling to `finance-safety-floor` / `strategy-safety-floor`. Every output is a **draft to PREPARE for attorney review**, never legal advice. Operating mechanics migrated to [`legal-practice-profile § Legal safety floor`](../skills/legal-practice-profile/SKILL.md) (per P4 of `road-to-kernel-and-router`) — the Iron Laws below stay here.
 
 ## Iron Law — no final legal call
 

package/dist/agent-src/rules/lethal-trifecta-guard.md

@@ -20,6 +20,8 @@ enforced_by:
 collision_ok:
   "src/skills/": "skill authoring reviews tool grants and the egress leg"
   "src/agent-src/commands/": "command authoring reviews the three trifecta legs"
+# obligation: line 60
+obligation_frequency: "per-edit"
 ---
 
 # Lethal-Trifecta Guard

package/dist/agent-src/rules/linked-projects-onboarding-gate.md

@@ -23,6 +23,8 @@ trust:
   confidence: medium
 install:
   removable: true
+# obligation: line 30
+obligation_frequency: "per-session"
 ---
 
 # Linked-Projects Onboarding Gate

package/dist/agent-src/rules/low-impact-corpus-privacy-floor.md

@@ -10,6 +10,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer]
 packs: [meta]
+# obligation: line 28
+obligation_frequency: "per-edit"
 ---
 
 # Low-Impact Corpus — Privacy Floor

package/dist/agent-src/rules/markdown-safe-codeblocks.md

@@ -9,6 +9,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 23
+obligation_frequency: "per-turn"
 ---
 
 # Markdown Safe Codeblocks

package/dist/agent-src/rules/media-governance-routing.md

@@ -36,6 +36,8 @@ collision_ok:
   "/audio:": "routes the media policy layer for audio surfaces"
   "/video:": "routes the media policy layer for video surfaces"
   "likeness": "likeness prompts must load the policy layer before generation"
+# obligation: line 46
+obligation_frequency: "per-event"
 ---
 
 # Media Governance Routing

package/dist/agent-src/rules/media-sync-ground-truth.md

@@ -17,6 +17,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, engineering, gtm]
 packs: [ai-video]
+# obligation: line 31
+obligation_frequency: "per-event"
 ---
 
 # Media Sync — Ground Truth Is the Audio

package/dist/agent-src/rules/minimal-safe-diff.md

@@ -17,6 +17,8 @@ enforced_by:
   - "hook:minimal-safe-diff"
 collision_ok:
   "fix": "a fix is the smallest change that solves the stated problem"
+# obligation: line 25
+obligation_frequency: "per-edit"
 ---
 
 # Minimal Safe Diff

package/dist/agent-src/rules/missing-tool-handling.md

@@ -9,6 +9,8 @@ routes_to:
   - "guideline:agent-infra/missing-tool-handling"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 16
+obligation_frequency: "per-event"
 ---
 
 # Missing Tool Handling

package/dist/agent-src/rules/model-recommendation.md

@@ -13,6 +13,8 @@ routes_to:
   - "guideline:agent-infra/model-recommendation"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 4
+obligation_frequency: "per-task"
 ---
 
 # Model Recommendation

package/dist/agent-src/rules/no-attribution-footers.md

@@ -8,6 +8,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 18
+obligation_frequency: "per-commit"
 ---
 
 # No Attribution Footers

package/dist/agent-src/rules/no-decorative-emojis-in-git-surfaces.md

@@ -17,6 +17,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 27
+obligation_frequency: "per-commit"
 ---
 
 # No Decorative Emojis in Git Surfaces

package/dist/agent-src/rules/no-pr-progress-comments.md

@@ -10,6 +10,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
+# obligation: line 20
+obligation_frequency: "per-commit"
 ---
 
 # No Unsolicited PR Progress Comments
@@ -23,7 +25,9 @@ EXCEPTION: USER-INVOKED FLOWS ALWAYS RUN.
 EXCEPTION: USER EXPLICITLY ASKED FOR IT THIS TURN.
 ```
 
-Reading `.agent-settings.yml`:
+Reading `.agent-settings.yml` — the project layer of a cascade that starts
+user-global, so "not set" means not set on any layer; `agent-config settings:get
+personal.pr_progress_comments` reports the value and the file it came from:
 
 - Missing key / not set → treat as `false`.
 - `personal.pr_progress_comments: false` (default) → gate fires.

package/dist/agent-src/rules/no-roadmap-references.md

@@ -22,6 +22,8 @@ enforced_by:
   - "validator:src/scripts/check_council_references.ts"
 collision_ok:
   "agents/roadmaps/": "roadmap edits are where transient-ref links get written"
+# obligation: line 47
+obligation_frequency: "per-edit"
 ---
 
 # No Transient References from Stable Artifacts

package/dist/agent-src/rules/notes-first-reasoning.md

@@ -17,6 +17,8 @@ workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 collision_ok:
   "debug": "debug hypotheses belong in the session notes file"
+# obligation: line 35
+obligation_frequency: "per-turn"
 ---
 
 # Notes-First Reasoning

package/dist/agent-src/rules/onboarding-gate.md

@@ -11,12 +11,16 @@ workspaces: [agent-config-maintainer, construction, engineering, finance, founde
 packs: [meta]
 enforced_by:
   - "hook:onboarding-gate"
+# obligation: line 18
+obligation_frequency: "per-session"
 ---
 
 # Onboarding Gate
 
 **Iron Law.** First turn of a project: if `onboarding.onboarded` is
-false in `.agent-settings.yml`, instruct the developer to run
+false in `.agent-settings.yml` — the project layer of a cascade that starts
+user-global, so check it with `agent-config settings:get onboarding.onboarded`
+rather than by opening one file — instruct the developer to run
 `agent-config setup` in their terminal before executing any other
 request. The wizard writes `onboarding.onboarded: true` on `Finish`,
 which silences this rule for subsequent turns.

package/dist/agent-src/rules/output-discipline.md

@@ -12,6 +12,8 @@ workspaces: [engineering]
 packs: [engineering-base]
 enforced_by:
   - "validator:src/scripts/lint_output_slop.ts"
+# obligation: line 22
+obligation_frequency: "per-edit"
 ---
 
 # Output Discipline

package/dist/agent-src/rules/package-ci-checks.md

@@ -10,6 +10,8 @@ routes_to:
   - "skill:lint-skills"
 workspaces: [agent-config-maintainer]
 packs: [meta]
+# obligation: line 17
+obligation_frequency: "per-commit"
 ---
 
 # Package Ci Checks

package/dist/agent-src/rules/persona-governance.md

@@ -27,6 +27,8 @@ workspaces: [agent-config-maintainer]
 packs: [meta]
 enforced_by:
   - "validator:src/scripts/lint_persona_governance.ts"
+# obligation: line 41
+obligation_frequency: "per-edit"
 ---
 
 # Persona Governance

package/dist/agent-src/rules/php-coding.md

@@ -18,6 +18,8 @@ install:
   removable: true
 collision_ok:
   "phpstan": "phpstan findings are the PHP pattern floor's own quality surface"
+# obligation: line 25
+obligation_frequency: "per-edit"
 ---
 
 # Php Coding

package/dist/agent-src/rules/prefer-enums-over-literals.md

@@ -15,6 +15,8 @@ packs: [engineering-base]
 collision_ok:
   "migration": "migrations add columns — multi-state fields should land as enums from the start"
   "category": "a category field is the canonical enum candidate"
+# obligation: line 27
+obligation_frequency: "per-edit"
 ---
 
 # Prefer Enums Over Literal Values

package/dist/agent-src/rules/preservation-guard.md

@@ -15,6 +15,8 @@ packs: [meta]
 enforced_by:
   - "validator:src/scripts/check_condensation.ts"
   - "validator:src/scripts/skill_linter.ts"
+# obligation: line 22
+obligation_frequency: "per-edit"
 ---
 
 # Preservation Guard

package/dist/agent-src/rules/provider-lifecycle-discipline.md

@@ -30,6 +30,8 @@ collision_ok:
   "/audio:": "provider-tier gate for audio providers"
   "/video:": "provider-tier gate for video providers"
   "scripts/ai-image/adapters/": "adapter edits are the lifecycle contract's surface"
+# obligation: line 41
+obligation_frequency: "per-event"
 ---
 
 # Provider Lifecycle Discipline

package/dist/agent-src/rules/question-not-instruction.md

@@ -24,6 +24,8 @@ applies_to_user_types:
 self_contained: true
 workspaces: [engineering]
 packs: [meta]
+# obligation: line 32
+obligation_frequency: "per-turn"
 ---
 
 # Question Is Not an Instruction

package/dist/agent-src/rules/reviewer-awareness.md

@@ -13,6 +13,8 @@ routes_to:
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 roles: [reviewer]
+# obligation: line 20
+obligation_frequency: "per-commit"
 ---
 
 # Reviewer Awareness

package/dist/agent-src/rules/roadmap-ci-steps-policy.md

@@ -30,6 +30,8 @@ packs: [meta]
 roles: [planner]
 collision_ok:
   "agents/roadmaps/": "roadmap steps must not schedule CI-shaped gates"
+# obligation: line 41
+obligation_frequency: "per-edit"
 ---
 
 # Roadmap CI-Steps Policy
@@ -43,7 +45,10 @@ AND EXECUTION MUST SKIP THEM INLINE WITH [-] AND A REASON.
 ```
 
 When autonomous local-CI runs are disabled in `.agent-settings.yml`
-(`quality.local_auto_run: false` — the shipped template default), every
+(`quality.local_auto_run: false` — the shipped template default; that file is the
+project layer of a cascade that starts user-global, and this key is one where an
+ABSENT value resolves to `true` at its reader and therefore DISABLES this gate —
+`agent-config settings:get quality.local_auto_run` reports both facts), every
 full-pipeline gate run during roadmap work is wasted wall-clock and
 tokens — the remote CI on the PR is the authoritative gate. Roadmaps must
 neither schedule nor execute those gates locally. New CI gates and

package/dist/agent-src/rules/roadmap-progress-sync.md

@@ -16,6 +16,8 @@ enforced_by:
   - "hook:roadmap-progress"
 collision_ok:
   "agents/roadmaps/": "any roadmap touch regenerates the dashboard, same response"
+# obligation: line 26
+obligation_frequency: "per-edit"
 ---
 
 # Roadmap Progress Sync

package/dist/agent-src/rules/role-mode-adherence.md

@@ -9,6 +9,8 @@ triggers:
 self_contained: true
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+# obligation: line 23
+obligation_frequency: "per-turn"
 ---
 
 # Role Mode Adherence
@@ -18,7 +20,7 @@ one of the six modes defined in
 [`role-contracts`](../docs/guidelines/agent-infra/role-contracts.md):
 `developer`, `reviewer`, `tester`, `po`, `incident`, `planner`.
 
-Read `roles.active_role` from `.agent-settings.yml` at session start. Empty / missing → rule is inert; do NOT guess a mode.
+Read `roles.active_role` from `.agent-settings.yml` at session start — the project layer of a cascade that starts user-global, so use `agent-config settings:get roles.active_role`, which reports the value and the file it came from, rather than opening one file. Empty / missing → rule is inert; do NOT guess a mode.
 
 When active, every closing output MUST:
 

package/dist/agent-src/rules/rule-type-governance.md

@@ -10,6 +10,8 @@ workspaces: [agent-config-maintainer]
 packs: [meta]
 collision_ok:
   "src/rules/": "the always-vs-auto choice fires on every rule edit"
+# obligation: line 17
+obligation_frequency: "per-edit"
 ---
 
 # Rule Type Governance