@event4u/agent-config 9.12.0 → 9.14.0

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

@@ -0,0 +1,147 @@
+---
+model_tier: high
+name: optimize-deep
+pack: meta
+tier: 2
+visibility: internal
+sub: deep
+cluster: optimize
+skills: [ai-council, roadmap-writing, subagent-orchestration, decision-review]
+description: "Autonomous deep-refactoring loop — subagent analysis, verified findings, council, central + sub-roadmaps, PR, then N refinement loops (default 3). E.g. 'run a deep optimization pass'."
+argument-hint: "[--loops=N] [--scope=<path>] [--no-external]"
+suggestion:
+  eligible: false
+  rationale: "Cluster sub-command — reached via its cluster head's routing or its explicit /cluster:sub name; not independently suggested (surface-consolidation)."
+workspaces:
+  - agent-config-maintainer
+  - engineering
+packs:
+  - meta
+---
+
+# /optimize-deep
+
+Autonomous deep-improvement loop: **analyze → verify → council → roadmaps →
+PR → refine ×N**. The autonomous sibling of [`/optimize project`](project.md)
+(which is interview-driven and asks the user); this command answers its own
+questions in the AI council and ends with a pull request plus a
+council-refined roadmap set.
+
+This is a **coordinator** over existing primitives — it composes, never
+reimplements: subagent fan-out analysis, `/analyze:decision`-style decision
+challenge, `ai-council` resolution, `/roadmap:create` output shape,
+`/create-pr` mechanics.
+
+## When to invoke
+
+- "Deep-analyze this package and build the improvement roadmap" /
+  "geh in die Tiefe und erstelle die Refactoring-Roadmap".
+- Periodic renewal: question standing decisions after the environment
+  changed (new host capabilities, model generation, ecosystem shift).
+- A refactoring mandate that should end in a reviewed PR, not a chat answer.
+
+Do NOT invoke for: a single named bug, an interview-style sweep with the
+user in the loop (route to `/optimize project`), a code-only analysis
+(`/project-analyze`), or agent-layer file tooling (`/optimize` siblings).
+
+## Loop budget
+
+`--loops=N` caps the refinement loops. **Default: 3** (council-locked
+2026-08-02: autonomous loops without a fast, trustworthy CI oracle are
+compounding-error machines; 3 with a tripwire beats 5 on cost/benefit).
+Hard ceiling: 5 — above that, re-invoke deliberately with fresh context.
+
+**Halt-on-spin tripwire (checked after every loop, overrides the budget):**
+
+- A loop ends with no material roadmap delta (no step added, removed,
+  re-scoped, or re-ordered) → STOP, the set has converged.
+- The council splits on the same question twice → STOP, escalate that
+  question to the user instead of burning a third loop on it.
+- Any validation target fails 3 consecutive refinement attempts → STOP
+  (N=3 budget, `autonomous-execution`).
+
+## Steps
+
+### Step 0 — Preflight (read-only)
+
+1. Live remote state first (`direct-answers` live-state law): fetch,
+   open PRs, recently merged work overlapping the scope — never from memory.
+2. Create or enter an isolated worktree on a fresh branch off the trunk
+   (branch/worktree creation is authorized by invoking this command; every
+   Hard-Floor action below stays gated).
+3. Honor any repo worktree-seeding convention when seeding the worktree;
+   never copy `.agent-settings.yml` into a worktree.
+4. Read the lock inventory: honest nulls, DR memories, `later/` resume
+   conditions, standing ADRs. These are constraints for Step 4, surfaced —
+   never silently relitigated (`decision-revisit-gate`).
+
+### Step 1 — Deep analysis (parallel subagents)
+
+Fan out read-only analysis subagents over the repo's load-bearing surfaces
+(token/context cost, execution flows, CI/PR pipeline, routing/activation,
+decision debt, archived intelligence) plus — unless `--no-external` —
+tree-level deep-dives of named external references (`external-reference-deep-dive`:
+file trees + raw files, never README summaries). Each agent returns
+structured findings with file:line evidence and an effort estimate.
+
+### Step 2 — Verification gate (non-negotiable)
+
+Hand-verify every damning finding before it may steer the roadmap
+(`plausible-mechanism-is-not-evidence`): re-run the grep/measurement the
+finding rests on, in this checkout, at this SHA. A finding that fails
+verification is dropped with a note. Findings colliding with a recorded
+lock are marked and routed to Step 3 only if the mechanism differs
+(mechanism-match test) — otherwise honored as locked.
+
+### Step 3 — Council pass
+
+Run the AI council (`council:estimate` → `council:run --confirm`) on the
+contested decisions only: priority order, roadmap topology, lock collisions
+that pass the mechanism-match test, and the loop count when the user gave
+none. Surface the fast-path marker verbatim where the low-impact path
+resolves something. High-impact and user-required classes still reach the
+user per `ai-council-config` — autonomy never rewires that floor.
+
+### Step 4 — Roadmap set
+
+Author ONE central roadmap (goal, verified findings, locks honored,
+sub-roadmap management table, pre-registered success criteria, provenance —
+external sources anonymized + `ENC1:`-encrypted per `source-confidentiality`)
+plus sub-roadmaps cut along the council's topology. Foundation-class
+work (whatever must be true for the rest to be verifiable — typically the
+CI oracle) gates the leverage-class work explicitly. Regenerate the
+dashboard (`roadmap:progress`) in the same response as any roadmap write.
+
+### Step 5 — Pull request
+
+Push the branch and open the PR per [`/create-pr`](../pr/create.md) — its
+mechanics and the always-active PR-surface rules govern the body and reply
+shape; do not restate them here.
+
+### Step 6 — Refinement loops (×N, autonomous)
+
+Each loop: (a) re-read the roadmap set with fresh subagent reviewers
+(adversarial: hunt over-building, missing evidence, lock violations,
+sequencing errors); (b) resolve contested deltas in the council; (c) any
+delta resting on a NEW factual claim re-enters the Step-2 verification gate
+before application — reviewer assertions are findings, not facts; (d) apply
+the surviving deltas to the roadmaps; (e) push to the same PR; (f) evaluate
+the tripwire. Loop output is a delta summary in the PR description's
+changelog section, not a comment (`no-pr-progress-comments`).
+
+## Output
+
+- The PR URL (literal last line of the closing reply).
+- Central + sub-roadmaps on the branch, dashboard regenerated.
+- Council artifacts under `agents/runtime/council/` (local-only, auto-pruned).
+- A one-paragraph verdict per refinement loop: what changed, what converged.
+
+## Gotchas
+
+- Merge/deploy is where autonomy ends — Step 6 loop pushes go to the
+  already-open PR under the invocation's authorization; merging it,
+  deploying, or any irreversible external action stays this-turn gated.
+- Council spend: estimate first; abort and surface if the configured budget
+  guard trips mid-run.
+- Subagent cwd pins to the launch dir, not the worktree — pass absolute
+  paths into every subagent prompt.

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

@@ -2,19 +2,19 @@
 model_tier: medium
 name: optimize
 disable-model-invocation: true
-argument-hint: "[skills|agents-dir|augmentignore|rtk|project|prompt] [args]"
+argument-hint: "[skills|agents-dir|augmentignore|rtk|project|prompt|deep] [args]"
 pack: meta
-intent: "Optimization dispatcher — skills, rtk, augmentignore, agents-dir, project sweep, prompt"
-routes_to: [optimize-skills, optimize-rtk, optimize-augmentignore, optimize-agents-dir, optimize-project, optimize-prompt]
+intent: "Optimization dispatcher — skills, rtk, augmentignore, agents-dir, project sweep, prompt, deep autonomous loop"
+routes_to: [optimize-skills, optimize-rtk, optimize-augmentignore, optimize-agents-dir, optimize-project, optimize-prompt, optimize-deep]
 replaces: []
 tier: 1
 visibility: advanced
-description: Optimize orchestrator — routes to skills, agents-dir, augmentignore, rtk-filters, project (project-wide sweep), prompt (AI-prompt polish)
+description: Optimize orchestrator — routes to skills, agents-dir, augmentignore, rtk-filters, project (project-wide sweep), prompt (AI-prompt polish), deep (autonomous deep-refactoring loop)
 cluster: optimize
 type: orchestrator
 suggestion:
   eligible: true
-  trigger_description: "optimize my skills, manage agents directory, tune augmentignore, optimize rtk filters, optimize this project, optimize this prompt"
+  trigger_description: "optimize my skills, manage agents directory, tune augmentignore, optimize rtk filters, optimize this project, optimize this prompt, run a deep optimization pass"
   trigger_context: "maintainer auditing/trimming the agent layer, running a project-wide optimization sweep, or polishing an AI prompt (NOT AGENTS.md — that's /agents)"
 workspaces:
   - agent-config-maintainer
@@ -42,6 +42,7 @@ the **agent layer** (skills, agents-dir, augmentignore, rtk), the **project**
 | `/optimize rtk` | `commands/optimize/rtk.md` | Create or refine project-local rtk filters |
 | `/optimize project` | `commands/optimize/project.md` | Project-wide optimization sweep — inventory roadmaps/ADRs/agent folders, challenge stale decisions, emit new roadmap(s) |
 | `/optimize prompt` | `commands/optimize/prompt.md` | Optimize a raw prompt for ChatGPT/Claude/Gemini via the 4-D methodology |
+| `/optimize deep` | `commands/optimize/deep.md` | Autonomous deep-refactoring loop — subagent analysis, council, central + sub-roadmaps, PR, N refinement loops (default 3) |
 
 Sub-command names match the locked contract in
 [`docs/contracts/command-clusters.md`](../docs/contracts/command-clusters.md).
@@ -60,14 +61,19 @@ Sub-command names match the locked contract in
    > 4. rtk — create or refine project-local rtk filters
    > 5. project — project-wide sweep (roadmaps, ADRs, decisions → new roadmaps)
    > 6. prompt — polish a raw AI prompt (4-D methodology)
+   > 7. deep — autonomous deep-refactoring loop (analysis → council → roadmaps → PR → refine ×N)
 
 ## Rules
 
 - **Suggest only — never auto-apply.** All `/optimize` sub-commands are
   audit-grade: they report and propose, but the user approves every change.
+  Exception: `deep` is the explicitly autonomous variant — invoking it IS the
+  approval for its worktree/branch/roadmap/PR flow; the Hard Floor
+  (merge/deploy/prod/bulk-delete) still gates inside it.
 - **Scope check before routing.** Agent-layer subs (1–4) never touch project
   code or roadmaps; `project` never rewrites the agent layer; `prompt` only
-  returns a rewritten prompt.
+  returns a rewritten prompt; `deep` writes roadmaps + a PR branch but never
+  merges.
 - **Do NOT chain sub-commands.** One `/optimize <sub>` per turn.
 - If the user invokes `/optimize` with no argument, **show the menu** — do
   not guess which sub-command they meant.

package/dist/agent-src/rules/active-remediation.md

@@ -4,8 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "Spotted an issue (security gap, missing test, bad code, duplication, stale idiom) — never ignore: small→fix inline, bigger→ask, many→follow-up PR"
 triggers:
-  - intent: "spotted an unrelated issue while working"
-  - intent: "found legacy or duplicated code"
   - keyword: "refactor"
   - keyword: "duplicate"
   - keyword: "legacy"

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

@@ -7,7 +7,6 @@ triggers:
   - keyword: "controller"
   - keyword: "service"
   - keyword: "module"
-  - intent: "structural decision"
 routes_to:
   - "skill:module-detect-on-the-fly"
 workspaces: [agent-config-maintainer, engineering]

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

@@ -4,10 +4,6 @@ tier: "2a"
 alwaysApply: false
 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"
   - phrase: "new skill"
   - phrase: "new rule"
   - phrase: "new command"

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

@@ -8,9 +8,8 @@ load_context:
   - ../contexts/execution/autonomy-mechanics.md
   - ../contexts/execution/autonomy-examples.md
 triggers:
-  - intent: "trivial workflow question"
-  - intent: "autonomy mode"
   - keyword: "personal.autonomy"
+  - phrase: "autonomy mode"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/rules/broken-access-control.md

@@ -4,8 +4,6 @@ tier: "2a"
 alwaysApply: false
 description: "Endpoint/query on user/tenant data — authenticated ≠ authorized: server-derived ownership/tenant/role + negative tests (401/non-owner/cross-tenant)"
 triggers:
-  - intent: "returning user or tenant data"
-  - intent: "adding an endpoint that reads a record by id"
   - keyword: "endpoint"
   - keyword: "route"
   - keyword: "authorization"

package/dist/agent-src/rules/code-comment-discipline.md

@@ -4,9 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "Writing/editing code — a comment states a WHY or constraint the code cannot show; never restate what names/types say; no signature-mirroring docblocks"
 triggers:
-  - intent: "writing or generating code"
-  - intent: "adding a class / method / function"
-  - intent: "refactoring code"
   - keyword: "comment"
   - keyword: "docblock"
   - keyword: "phpdoc"

package/dist/agent-src/rules/code-provenance.md

@@ -4,9 +4,6 @@ tier: "2a"
 alwaysApply: false
 description: "Porting/adapting external code (algorithm, structure, >~10 lines) — close the source, re-derive; conscious borrows need a ledger entry + license check"
 triggers:
-  - intent: "porting or adapting code from an external source"
-  - intent: "implementing an algorithm or structure seen in another project"
-  - intent: "reusing a snippet from online / another repo / a training-data recall"
   - keyword: "port this"
   - keyword: "adapt this"
   - keyword: "based on this repo"

package/dist/agent-src/rules/communication-through-line.md

@@ -3,11 +3,10 @@ type: "auto"
 tier: "2b"
 alwaysApply: false
 description: "Multi-step or continuation replies carry a red thread — goal once, each turn tied to it, name what changed, close with one end-summary"
-triggers:
-  - intent: "producing a multi-step or continuation reply"
-  - intent: "reporting progress on ongoing work"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
+triggers:
+  - phrase: "reporting progress"
 ---
 
 # Communication Through-Line

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

@@ -3,8 +3,6 @@ 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"

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

@@ -4,10 +4,8 @@ tier: "1"
 alwaysApply: false
 description: "Debugging, fixing errors, or long conversations — 3-failure stop rule, tool-loop detection, fresh-chat triggers"
 triggers:
-  - intent: "long conversation"
-  - intent: "tool loop"
-  - intent: "fresh chat"
   - keyword: "3-failure"
+  - phrase: "long conversation"
 routes_to:
   - "guideline:agent-infra/context-hygiene-mechanics"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]

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

@@ -5,8 +5,6 @@ description: "Beneficial change blocked by a lock (honest-null, don't-relitigate
 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"

package/dist/agent-src/rules/design-fidelity.md

@@ -9,10 +9,21 @@ triggers:
   - keyword: "design system"
   - keyword: "design spec"
   - keyword: "Figma"
+  - keyword: "handoff"
+  - keyword: "Claude Design"
   - phrase: "match the design"
   - phrase: "build this design"
   - phrase: "design fidelity"
   - phrase: "stick to the design"
+  - phrase: "design.html"
+  - phrase: "attached artifact"
+  - phrase: "provided artifact"
+  - phrase: "übernimm das design"
+  - phrase: "baue das nach"
+  - phrase: "bau das nach"
+  - phrase: "1:1 um"
+  - phrase: "1:1 nach"
+  - file_pattern: "*design.html"
 applies_to_user_types:
   - "creator"
   - "developer"
@@ -73,6 +84,24 @@ porting, or modifying UI to match it.
 - The user explicitly invites exploration ("show me options", "redesign this", "improve the layout") — that authorises deviation for that turn.
 - Non-UI surfaces (scripts, CLI, backend).
 
+## Routing — an attached artifact is a trigger, an attached HTML file is not
+
+Matching is plain lower-cased substring containment on the prompt, plus fnmatch
+over the open files. Three handover classes must reach this rule: an English
+phrasing, a German one, and a prompt carrying **no** keyword at all because the
+artifact is simply attached. The last is covered by `file_pattern: *design.html`
+— the conventional handover filename, not `*.html`, which would fire on every
+HTML edit in every project and be strictly worse than the gap it closes. A
+handover under some other filename needs one word in the prompt.
+
+The trigger set is deliberately phrase-heavy on the German side and on
+`artifact`: a bare `artifact` keyword fires on "the CI build artifact is 40 MB".
+`ROUTING_MATRIX` in
+[`design_fidelity_routing.test.ts`](../../tests/scripts/design_fidelity_routing.test.ts)
+pins both halves — every class that must route, and the near-misses that must
+stay silent (fixture `daf-port-trigger-de`). Extending the set without adding a
+near-miss row there is how an over-broad trigger lands.
+
 Body migrated to [`guideline:design-fidelity-mechanics`](../docs/guidelines/design-fidelity-mechanics.md) (per P4 of `road-to-kernel-and-router.md`) — surgical visual edits (targeted-edit vs redesign-trigger discipline, stable anchors), asset & imagery discipline (owned-asset path, third-party delivery is self-hosted by default, real-imagery-as-proof, iconography floor, no unrequested filler), deviation-surfacing shape, failure-mode catalog, `daf-*` fixtures.
 Trigger-set above activates this routing on demand, independent of the discipline profile (ADR-110).
 

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

@@ -4,9 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "Adopting a new domain track (mobile, ML, IoT…) — demand/owner/CI gates BEFORE harvest"
 triggers:
-  - intent: "adopt new domain"
-  - intent: "harvest new domain track"
-  - intent: "open a domain plate"
   - keyword: "mobile track"
   - keyword: "ml track"
   - keyword: "blockchain track"

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

@@ -4,7 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "After EVERY code edit, find ALL downstream changes — callers, tests, imports, types, documentation"
 triggers:
-  - intent: "after code edit"
   - keyword: "callers"
   - keyword: "imports"
   - keyword: "downstream"
@@ -81,6 +80,16 @@ Next.js / Python / Go) live in [`agent-docs-writing`](../skills/agent-docs-writi
 Before making a change that affects a **public API** (endpoint response, service method signature,
 event payload, job constructor), assess the impact:
 
+**Why the surface, not just the contract, is the thing to keep small** (Hyrum's
+Law): with enough consumers, every *observable* behaviour of a system becomes
+something somebody depends on, regardless of what the documented contract
+promises — iteration order, an error message's wording, a timing side effect, a
+field that happens to be present. Two consequences, and they point in opposite
+directions. Adding: a smaller exported surface is fewer accidental contracts to
+honour later, so do not export what the caller does not need. Removing: the
+list above is a floor, not a ceiling — an observable behaviour nobody documented
+can still break someone when it disappears.
+
 ### Always ask the user first when:
 
 - Removing or renaming a public method/class

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

@@ -4,13 +4,6 @@ tier: "2b"
 description: "User names an external repo/file/URL as reference — fetch the actual tree and inspect; never summarize from README"
 alwaysApply: false
 triggers:
-  - intent: "look at how X does it"
-  - intent: "compare with reference repo"
-  - intent: "use as template / vorlage"
-  - intent: "wie macht es X"
-  - intent: "vergleiche mit Y"
-  - intent: "schau dir Z an"
-  - intent: "study this competitor"
   - keyword: "github.com/"
   - keyword: "source of truth"
   - phrase: "reference repo"

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

@@ -7,7 +7,6 @@ triggers:
   - keyword: "fast-path"
   - keyword: "Resolved via low-impact council"
   - keyword: "low_impact"
-  - intent: "low-impact council dispatch"
 validator_ignore:
   - type: "substring"
     pattern: ".agent-src.uncondensed/"

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

@@ -4,13 +4,6 @@ tier: "2a"
 alwaysApply: false
 description: "Git history — no unasked rebase/squash/amend; never drop foreign commits; pushed rewrite → re-push same turn"
 triggers:
-  - intent: "rebase the branch"
-  - intent: "squash commits"
-  - intent: "clean up commit history"
-  - intent: "fold this into the previous commit"
-  - intent: "tidy history after pushing"
-  - intent: "reseat the branch base"
-  - intent: "exclude these commits from the branch"
   - keyword: "git rebase"
   - keyword: "rebase --onto"
   - keyword: "reset --hard"

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

@@ -6,8 +6,6 @@ alwaysApply: false
 load_context:
   - ../contexts/communication/rules-auto/guidelines-mechanics.md
 triggers:
-  - intent: "writing code"
-  - intent: "reviewing code"
   - keyword: "convention"
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]

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

@@ -5,8 +5,6 @@ description: "Before features or architectural changes — validate against exis
 alwaysApply: false
 council_depth: deep
 triggers:
-  - intent: "implement feature"
-  - intent: "architectural change"
   - keyword: "refactor"
   - keyword: "implement"
   - keyword: "migration"
@@ -42,6 +40,10 @@ Before implementing:
 
 On a "build me an app / add this feature" ask, ONE reflexive pre-check before the three checks: **who asked · what breaks if unbuilt · what's the evidence?** Recommend **build** only at a real retention/activation blocker (evidence, not anxiety); else **defer/validate**, naming the missing evidence. Advisory — "just build it" proceeds immediately; no network lookup. Hierarchy + build/defer table: guideline § 8-pre.
 
+## The solution-size ladder — stop at the first rung that works
+
+Once the demand gate says build, "does this already exist?" has an **ordered** answer set: need-to-exist → reuse-in-repo → stdlib / framework → **native platform** → installed dependency → smallest working form. Stop at the first rung that carries the requirement. Ordered **after** comprehension — it shortens the solution, never the reading. Two axes, not one: the ladder is *scope*; **shape** is the other half — of what must exist, the form with the least cognitive load, explicitly not the fewest keystrokes. Rungs, the platform-rung examples, and the precedence order when they pull against each other: guideline § 8b-ladder / § 8b-shape / § 8b-precedence.
+
 ## The three checks
 
 Run, in order: **1. Is the request clear?** · **2. Does it fit the existing architecture?** · **3. Is the approach sound?**

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

@@ -5,10 +5,6 @@ description: "Before executing a complex plan — ask 'am I solving the right pr
 alwaysApply: false
 council_depth: deep
 triggers:
-  - intent: "complex plan"
-  - intent: "design decision"
-  - intent: "architectural plan"
-  - intent: "multi-step implementation"
   - keyword: "plan"
   - keyword: "design"
   - keyword: "architecture"

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

@@ -4,8 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "IDE-attached sibling repo detected — prompt once to opt into cross-repo awareness, persist local-only"
 triggers:
-  - intent: "work across two projects"
-  - intent: "sibling repository"
   - keyword: "linked project"
   - keyword: "cross-repo"
   - keyword: "sibling repo"

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

@@ -4,7 +4,6 @@ tier: "2b"
 description: "Generating markdown with code blocks — prevent broken nesting"
 alwaysApply: false
 triggers:
-  - intent: "markdown with code blocks"
   - keyword: "triple backticks"
   - file_pattern: "*.md"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]

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

@@ -4,11 +4,11 @@ tier: "2a"
 alwaysApply: false
 description: "Writing or reviewing a diff — smallest change that solves the problem; no drive-by edits or reformatting"
 triggers:
-  - intent: "writing a diff"
-  - intent: "reviewing a diff"
   - keyword: "drive-by"
   - keyword: "rewrite"
   - keyword: "fix"
+  - phrase: "from scratch"
+  - phrase: "second system"
 routes_to:
   - "guideline:agent-infra/minimal-safe-diff-mechanics"
 workspaces: [engineering]

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

@@ -5,7 +5,6 @@ description: "CLI tool needed for the task is not installed — ask before worki
 triggers:
   - keyword: "command not found"
   - keyword: "not installed"
-  - intent: "install tool"
 routes_to:
   - "guideline:agent-infra/missing-tool-handling"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]

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

@@ -4,9 +4,6 @@ tier: "3"
 alwaysApply: false
 description: "PR/issue/comment/commit bodies — no 'Generated with' / 'Co-authored by' / 'opened by' attribution footers"
 triggers:
-  - intent: "PR body"
-  - intent: "commit message"
-  - intent: "Jira comment"
   - keyword: "co-authored"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]

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

@@ -4,13 +4,16 @@ tier: "3"
 alwaysApply: false
 description: "PR/issue/commit titles and comments — no decorative emojis; bodies only with an in-artifact legend"
 triggers:
-  - intent: "PR title"
-  - intent: "PR body"
-  - intent: "commit message"
-  - intent: "issue title"
-  - intent: "post PR comment"
   - keyword: "gh pr create"
   - keyword: "git commit"
+  - keyword: "🤖"
+  - keyword: "🚀"
+  - keyword: "🎉"
+  - keyword: "✨"
+  - keyword: "🔥"
+  - keyword: "💡"
+  - keyword: "👍"
+  - keyword: "❤️"
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 ---

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

@@ -4,11 +4,9 @@ tier: "2a"
 alwaysApply: false
 description: "PR comments — no unsolicited progress/status/CI narration unless personal.pr_progress_comments is true"
 triggers:
-  - intent: "post PR comment"
-  - intent: "PR status update"
-  - intent: "CI fix progress"
   - keyword: "gh pr comment"
   - keyword: "PullRequestComment"
+  - phrase: "status comment"
 workspaces: [agent-config-maintainer, engineering]
 packs: [meta]
 ---

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

@@ -8,8 +8,6 @@ triggers:
   - path_prefix: "agents/runtime/council/questions/"
   - path_prefix: "agents/runtime/council/responses/"
   - path_prefix: "agents/runtime/council/sessions/"
-  - intent: "link from stable artifact"
-  - intent: "link to council artefact"
 routes_to:
   - "skill:ai-council"
   - "skill:agent-docs-writing"

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

@@ -3,7 +3,6 @@ type: "auto"
 tier: "2a"
 description: "No placeholder prose in generated code/UI — no truncation shorthands; on budget overflow emit a clean PAUSED breakpoint"
 triggers:
-  - intent: "generating code or multi-section output"
   - keyword: "// rest of component"
   - keyword: "for brevity"
   - keyword: "rest follows the same pattern"

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

@@ -4,8 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "Field with multiple non-boolean states — prefer an enum over string/numeric literals; old-style literals found → note, finish the task, ask after"
 triggers:
-  - intent: "modeling a field with multiple states"
-  - intent: "adding a status or type field"
   - keyword: "enum"
   - keyword: "status"
   - keyword: "kind"

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

@@ -4,9 +4,6 @@ tier: "2b"
 alwaysApply: false
 description: "Merging/refactoring/condensing skills, rules, commands, or guidelines — prevent quality loss"
 triggers:
-  - intent: "merge skill"
-  - intent: "condense rule"
-  - intent: "refactor artifact"
   - keyword: "Iron Law"
 validator_ignore:
   - type: "substring"

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

@@ -6,7 +6,6 @@ alwaysApply: false
 triggers:
   - keyword: "active_role"
   - keyword: "role-mode"
-  - intent: "mode marker"
 workspaces: [agent-config-maintainer, construction, engineering, finance, founder, gtm, legal-review-prep, ops, product, small-business]
 packs: [meta]
 ---

package/dist/agent-src/rules/secret-vcs-guard.md

@@ -4,8 +4,6 @@ tier: "2a"
 alwaysApply: false
 description: "Writing a credential into a tracked file or committing one in any VCS (git/svn/hg) — STOP, show the match, ask, offer alternatives; never silently"
 triggers:
-  - intent: "writing a credential or API key into a file"
-  - intent: "committing or staging changes that may contain a secret"
   - keyword: "secret"
   - keyword: "password"
   - keyword: "credential"