@event4u/agent-config 11.0.0 → 12.1.0

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

@@ -7,7 +7,6 @@ pack: git
 intent: "Open a pull request with a generated description and stripped attribution footers"
 routes_to: [git-workflow]
 replaces: [create-pr]
-tier: 1
 visibility: advanced
 cluster: git-pr-create
 skills: [git-workflow]
@@ -71,16 +70,28 @@ Run, in order:
 1. **Ask the gate, never hand-roll the comparison:**
 
    ```bash
-   ./scripts-run src/scripts/check_branch_freshness
+   npx tsx node_modules/@event4u/agent-config/src/scripts/check_branch_freshness.ts
    ```
 
    It resolves the base itself — explicit `--base`, else the base of the **open
-   PR for this branch** as the forge reports it, else the repo default from
-   `origin/HEAD`. Do **not** substitute `git rev-list --count HEAD..origin/main`:
-   that hardcodes a base this branch may not target, and it reads the local
-   tracking ref, which is a fetch from earlier in the session — a memory, not a
-   check (`direct-answers` Iron Law 2). Exit `0` = current, `1` = behind, and the
-   refusal names the base **and where that base came from**.
+   PR for this branch** as the forge reports it, else the repo default the server
+   reports for `HEAD`. Do **not** substitute
+   `git rev-list --count HEAD..origin/main`: that hardcodes a base this branch may
+   not target, and it reads the local tracking ref, which is a fetch from earlier
+   in the session — a memory, not a check (`direct-answers` Iron Law 2).
+
+   **Exit `0` is not a verdict — it means only "did not refuse".** `1` = behind.
+   `0` covers "current", "could not verify", and every path with nothing to
+   check: a no-op in CI, a detached HEAD, and standing on the base branch
+   itself. Read the line, not just the status. A run that could not reach the
+   base prints `NOT VERIFIED` and still exits `0`, deliberately, so an offline
+   push is never blocked by a network failure; treating that as a clean pass is
+   the one misread this gate cannot protect you from.
+
+   **And under `--quiet` a genuine pass prints nothing at all** — that is how
+   `taskfiles/ci-fast.yml` invokes it, so silence there is the success case, not
+   a missing verdict. Every path that has NOT verified stays loud even under
+   `--quiet`. Run it without the flag when you need to read a verdict.
 
 2. `gh pr list --state open --base {resolved-base} --limit 20 --json number,headRefName,files`
    — open PRs targeting the same base, for the overlap question below.
@@ -89,10 +100,13 @@ Run, in order:
 
 | Gate | Overlapping open PR touches same files? | Action |
 |---|---|---|
-| exit `0` | — | Proceed to Step 2 |
+| exit `0`, prints `branch is current` | — | Proceed to Step 2 |
 | exit `1` | No | **Merge the base in** — `git fetch origin && git merge origin/{resolved-base} --no-edit` — then run the regeneration set below, then proceed. No need to ask; state that you did it. |
 | exit `1` | **Yes** | STOP — surface the overlapping PR number, ask: stack on top of it / wait for it to land / proceed-anyway-and-accept-conflicts / cancel |
+| exit `0`, prints `NOT VERIFIED` | — | The base could not be reached, so freshness is **unknown** — not confirmed. Re-run once; if it persists, say the check did not run rather than reporting a pass. A base that `ls-remote` cannot resolve (deleted or renamed after the PR opened, or a fork base) lands here too. |
 | warns `could not ask the forge` | — | The **default** base was checked and an open PR against a different base was **not** ruled out. Say so; do not report it as a clean freshness pass. |
+| exit `0`, prints nothing, `--quiet` given | — | The success case for the preflight invocation. Any non-verifying path would have printed even under `--quiet`. |
+| exit `0`, says `standing on <base> itself` / `detached HEAD` / `no-op in CI` | — | Nothing to check — a branch cannot be behind itself, a detached HEAD has no branch, and in CI the forge owns mergeability. Not a freshness pass; do not cite it as one. |
 
 A branch behind its base is **not** current — bring the base in **before** the PR
 exists, never after. Auto-merge when there is no file overlap (the common case);

package/dist/agent-src/commands/prediction-pool.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: prediction-pool
 pack: fun
-tier: 2
 visibility: internal
 description: "Fill a prediction pool (kicktipp, football/basketball WM): optimize expected points under the rules, enter tips via Playwright. Triggers 'Tippspiel', 'kicktipp', 'predict the pool'."
 argument-hint: "[event] [--pool-url <url>] [--council off|event|match] [--submit] [--fresh|--continue]"

package/dist/agent-src/commands/prepare-for-review.md

@@ -2,7 +2,6 @@
 model_tier: high
 name: prepare-for-review
 pack: engineering-base
-tier: 2
 visibility: internal
 skills: [git-workflow, quality-tools]
 description: Prepare a PR branch for local review — updates main and merges the full branch chain so the branch is up to date

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: profile-activate
 pack: meta
-tier: 2
 visibility: internal
 cluster: profile
 sub: activate

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: profile-deactivate
 pack: meta
-tier: 2
 visibility: internal
 cluster: profile
 sub: deactivate

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: profile-show
 pack: meta
-tier: 2
 visibility: internal
 cluster: profile
 sub: show

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: profile
 pack: meta
-tier: 2
 visibility: internal
 description: Session-profile orchestrator — activate / deactivate / show the active packs for this session (recommendation-bias surface filter, no persistence)
 argument-hint: "[activate|deactivate|show] [args]"

package/dist/agent-src/commands/project/analyze.md

@@ -2,7 +2,6 @@
 model_tier: high
 name: project-analyze
 pack: engineering-base
-tier: 2
 visibility: internal
 sub: analyze
 cluster: project

package/dist/agent-src/commands/project/health.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: project-health
 pack: engineering-base
-tier: 2
 visibility: internal
 sub: health
 cluster: project

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

@@ -7,7 +7,6 @@ pack: engineering-base
 intent: "Project dispatcher — full analysis or quick health check"
 routes_to: [project-analyze, project-health]
 replaces: []
-tier: 2
 visibility: internal
 description: Project orchestrator — routes to analyze (full audit) and health (read-only status check)
 cluster: project

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

@@ -5,7 +5,6 @@ pack: product-basic
 intent: "Refine a vague ticket into a clear, implementable spec"
 routes_to: [refine-ticket]
 replaces: []
-tier: 1
 visibility: advanced
 skills: [refine-ticket]
 description: Refine a Jira/Linear ticket before planning — rewritten ticket + Top-5 risks + persona voices, orchestrates validate-feature-fit and threat-modeling, ends with a close-prompt

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

@@ -2,7 +2,6 @@
 model_tier: high
 name: research-deep
 pack: product-discovery
-tier: 2
 visibility: internal
 cluster: research
 sub: deep

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

@@ -2,7 +2,6 @@
 model_tier: high
 name: research-report
 pack: product-discovery
-tier: 2
 visibility: internal
 cluster: research
 sub: report

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

@@ -4,7 +4,6 @@ name: research
 disable-model-invocation: true
 argument-hint: "[<topic>|deep|report] [args]"
 pack: product-discovery
-tier: 2
 visibility: internal
 cluster: research
 description: "Preliminary research scaffolder — pick objects, define fields, emit `outline.yaml` + `fields.yaml` for downstream deep research. Use for surveys, benchmarks, tech selection, competitive scans."

package/dist/agent-src/commands/review/changes.md

@@ -5,7 +5,6 @@ pack: engineering-base
 intent: "Multi-judge review of the current diff — bugs, security, tests, quality, architecture"
 routes_to: [code-review, judge-bug-hunter, judge-security-auditor, judge-test-coverage, judge-code-quality, architecture-review-lens]
 replaces: []
-tier: 2
 visibility: internal
 sub: changes
 cluster: review

package/dist/agent-src/commands/review/routing.md

@@ -2,7 +2,6 @@
 model_tier: high
 name: review-routing
 pack: engineering-base
-tier: 2
 visibility: internal
 sub: routing
 cluster: review

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

@@ -7,7 +7,6 @@ pack: engineering-base
 intent: "Review dispatcher — multi-judge self-review of the current diff, or reviewer routing"
 routes_to: [review-changes, review-routing]
 replaces: []
-tier: 1
 visibility: advanced
 description: Review orchestrator — routes to changes (five-judge self-review of the local diff) and routing (compute reviewer roles + historical bug patterns)
 cluster: review

package/dist/agent-src/commands/roadmap/ai-council.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: roadmap-ai-council
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: ai-council

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

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: roadmap-create
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: create

package/dist/agent-src/commands/roadmap/materialize.md

@@ -2,7 +2,6 @@
 model_tier: high
 name: roadmap-materialize
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: materialize

package/dist/agent-src/commands/roadmap/next.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: roadmap-next
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: next

package/dist/agent-src/commands/roadmap/process-full.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: roadmap-process-full
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: process-full

package/dist/agent-src/commands/roadmap/process-phase.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: roadmap-process-phase
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: process-phase

package/dist/agent-src/commands/roadmap/process-step.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: roadmap-process-step
 pack: product-basic
-tier: 2
 visibility: internal
 cluster: roadmap
 sub: process-step

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

@@ -7,7 +7,6 @@ pack: product-basic
 intent: "Roadmap dispatcher — create, process-step, process-phase, process-full, next, ai-council"
 routes_to: [roadmap-create, roadmap-ai-council, roadmap-materialize, roadmap-process-step, roadmap-process-phase, roadmap-process-full, roadmap-next]
 replaces: []
-tier: 1
 visibility: advanced
 description: Roadmap orchestrator — routes to create (authoring), process-step / process-phase / process-full (autonomous execution), and next (pick a roadmap and ship it).
 cluster: roadmap

package/dist/agent-src/commands/rule-compliance-audit.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: rule-compliance-audit
 pack: meta
-tier: 2
 visibility: internal
 skills: [rule-compliance-audit]
 description: Audit rule trigger quality, simulate activation, detect overlaps, find never-activating rules, and replay the router matcher over recent prompts (route:audit)

package/dist/agent-src/commands/security-audit-config.md

@@ -2,7 +2,6 @@
 model_tier: high
 name: security-audit-config
 pack: engineering-base
-tier: 2
 visibility: internal
 skills: [judge-security-auditor, threat-modeling, security-audit]
 description: Audit an assembled agent config (CLAUDE.md, .cursor/rules, settings, MCP, hooks, skills) for prompt-injection / supply-chain risk — A–F score per category, mapped to OWASP Agentic Top 10

package/dist/agent-src/commands/skill/preview.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: skill-preview
 pack: meta
-tier: 2
 visibility: internal
 cluster: skill
 sub: preview

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: skill
 pack: meta
-tier: 2
 visibility: internal
 description: Single-skill orchestrator — routes to preview. Non-destructive "what will this skill do?" before you run it.
 argument-hint: "[preview] <skill-name>"

package/dist/agent-src/commands/skills/discover.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: skills-discover
 pack: meta
-tier: 2
 visibility: internal
 cluster: skills
 sub: discover

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: skills
 pack: meta
-tier: 2
 visibility: internal
 description: Skill discovery orchestrator — routes to discover. Local, explained skill recommendations over the catalog + role shortlists + optional local analytics.
 argument-hint: "[discover] [role]"

package/dist/agent-src/commands/sync/agent-settings.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: sync-agent-settings
 pack: meta
-tier: 2
 visibility: internal
 sub: agent-settings
 cluster: sync

package/dist/agent-src/commands/sync/gitignore/fix.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: sync-gitignore-fix
 pack: meta
-tier: 2
 visibility: internal
 cluster: sync
 sub: gitignore

package/dist/agent-src/commands/sync/gitignore.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: sync-gitignore
 pack: meta
-tier: 2
 visibility: internal
 sub: gitignore
 cluster: sync

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

@@ -7,7 +7,6 @@ pack: meta
 intent: "Sync dispatcher — agent settings or the managed .gitignore block"
 routes_to: [sync-agent-settings, sync-gitignore, sync-gitignore-fix]
 replaces: []
-tier: 2
 visibility: internal
 description: Sync orchestrator — routes to agent-settings (template sync) and gitignore (managed block sync, plus legacy-cleanup fix)
 cluster: sync

package/dist/agent-src/commands/tdd/green.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tdd-green
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: tdd
 sub: green

package/dist/agent-src/commands/tdd/red.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tdd-red
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: tdd
 sub: red

package/dist/agent-src/commands/tdd/refactor.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tdd-refactor
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: tdd
 sub: refactor

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

@@ -4,7 +4,6 @@ name: tdd
 disable-model-invocation: true
 argument-hint: "[red|green|refactor] [behavior | args]"
 pack: engineering-base
-tier: 2
 visibility: internal
 description: TDD orchestrator — routes to red (failing test), green (minimum code), refactor (clean while green)
 cluster: tdd

package/dist/agent-src/commands/team/adversarial.md

@@ -4,7 +4,6 @@ name: team-adversarial
 disable-model-invocation: true
 argument-hint: "<focus>"
 pack: meta
-tier: 2
 visibility: internal
 skills: [adversarial-review]
 description: Thin wrapper — adversarial cross-model review on a named focus via the official plugin (/codex:adversarial-review). Escalation rung above the single-model adversarial-review skill.

package/dist/agent-src/commands/team/delegate.md

@@ -5,7 +5,6 @@ type: orchestrator
 disable-model-invocation: true
 argument-hint: "<task>"
 pack: meta
-tier: 2
 visibility: internal
 description: Thin wrapper — hand a task to the second model as a native worker via the official plugin (/codex:rescue). The only write-access wrapper; double-gated behind ai_team.allow_delegate.
 cluster: team

package/dist/agent-src/commands/team/review.md

@@ -4,7 +4,6 @@ name: team-review
 disable-model-invocation: true
 argument-hint: "[--background]"
 pack: meta
-tier: 2
 visibility: internal
 description: Thin wrapper — cross-model review of the current diff via the official plugin (/codex:review). Gated on /team availability (codex CLI + auth); fails closed when the plugin is absent.
 cluster: team

package/dist/agent-src/commands/team/status.md

@@ -3,7 +3,6 @@ model_tier: inherit
 name: team-status
 disable-model-invocation: true
 pack: meta
-tier: 2
 visibility: internal
 description: Thin wrapper — plugin job status via /codex:status plus a quota block (shared openai counter vs team + council ceilings). Gated on codex CLI/auth availability; fails closed without the plugin.
 cluster: team

package/dist/agent-src/commands/team-knowledge/bootstrap.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: team-knowledge-bootstrap
 pack: meta
-tier: 2
 visibility: internal
 cluster: team-knowledge
 sub: bootstrap

package/dist/agent-src/commands/team-knowledge/consolidate.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: team-knowledge-consolidate
 pack: meta
-tier: 2
 visibility: internal
 cluster: team-knowledge
 sub: consolidate

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

@@ -7,7 +7,6 @@ pack: meta
 intent: "Manage the repo-tracked team-knowledge layer — consolidate typed observation events into agents/knowledge/ pages, bootstrap a project baseline"
 routes_to: [team-knowledge-consolidate, team-knowledge-bootstrap]
 replaces: []
-tier: 2
 visibility: internal
 description: Team-knowledge orchestrator — routes to consolidate and bootstrap
 cluster: team-knowledge

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

@@ -7,7 +7,6 @@ pack: meta
 intent: "Route a cross-model team-mode request (review, adversarial, delegate, status) to the official plugin under ai_team governance"
 routes_to: [team-review, team-adversarial, team-delegate, team-status]
 replaces: []
-tier: 2
 visibility: internal
 description: Team orchestrator — governed cross-model access layer (a second strong model reviews the real diff; read-only multi-host fallback); routes to review, adversarial, delegate, status
 cluster: team

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tests-create
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: tests
 sub: create

package/dist/agent-src/commands/tests/e2e-heal.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tests-e2e-heal
 pack: engineering-base
-tier: 2
 visibility: internal
 replaces: [e2e-heal]
 sub: e2e-heal

package/dist/agent-src/commands/tests/e2e-plan.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tests-e2e-plan
 pack: engineering-base
-tier: 2
 visibility: internal
 replaces: [e2e-plan]
 sub: e2e-plan

package/dist/agent-src/commands/tests/execute.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: tests-execute
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: tests
 sub: execute

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

@@ -4,7 +4,6 @@ name: tests
 disable-model-invocation: true
 argument-hint: "[create|execute|e2e-plan|e2e-heal] [args]"
 pack: engineering-base
-tier: 2
 visibility: internal
 description: Tests orchestrator — routes to create, execute, e2e-plan, e2e-heal
 cluster: tests

package/dist/agent-src/commands/threat-model.md

@@ -2,7 +2,6 @@
 model_tier: high
 name: threat-model
 pack: engineering-base
-tier: 2
 visibility: internal
 skills: [threat-modeling, authz-review, security-sensitive-stop]
 description: Run a pre-implementation threat model on a proposed change — enumerates abuse cases, trust boundaries, and authorization gaps before the first line of code is written

package/dist/agent-src/commands/update-form-request-messages.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: update-form-request-messages
 pack: engineering-base
-tier: 2
 visibility: internal
 framework: laravel
 skills: [laravel-validation]

package/dist/agent-src/commands/upstream-contribute.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: upstream-contribute
 pack: meta
-tier: 2
 visibility: internal
 skills: [upstream-contribute, skill-writing, learning-to-rule-or-skill]
 description: Contribute a learning, skill, rule, or fix from a consumer project back to the shared agent-config package

package/dist/agent-src/commands/video/from-script.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: video-from-script
 pack: ai-video
-tier: 2
 visibility: internal
 cluster: video
 sub: from-script

package/dist/agent-src/commands/video/from-song.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: video-from-song
 pack: ai-video
-tier: 2
 visibility: internal
 cluster: video
 sub: from-song

package/dist/agent-src/commands/video/scene.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: video-scene
 pack: ai-video
-tier: 2
 visibility: internal
 cluster: video
 sub: scene

package/dist/agent-src/commands/video/stitch.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: video-stitch
 pack: ai-video
-tier: 2
 visibility: internal
 cluster: video
 sub: stitch

package/dist/agent-src/commands/video/storyboard.md

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: video-storyboard
 pack: ai-video
-tier: 2
 visibility: internal
 cluster: video
 sub: storyboard

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

@@ -2,7 +2,6 @@
 model_tier: inherit
 name: video
 pack: ai-video
-tier: 2
 visibility: internal
 cluster: video
 description: Video-creation orchestrator — Hollywood-level AI video pipeline. Routes to from-script, from-song, scene, storyboard, stitch.

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

@@ -5,7 +5,6 @@ pack: engineering-base
 intent: "Pick up the next sensible task and execute it autonomously"
 routes_to: [refine-prompt, command-routing]
 replaces: []
-tier: 0
 visibility: visible
 skills: [refine-prompt, command-routing]
 description: Drive a free-form prompt end-to-end through refine → score → plan → implement → test → verify → report — Option-A loop over the `work_engine` engine, confidence-band gated, no auto-git.

package/dist/agent-src/commands/worktree/cleanup.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: worktree-cleanup
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: worktree
 sub: cleanup

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

@@ -2,7 +2,6 @@
 model_tier: medium
 name: worktree-create
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: worktree
 sub: create

package/dist/agent-src/commands/worktree/status.md

@@ -2,7 +2,6 @@
 model_tier: medium
 name: worktree-status
 pack: engineering-base
-tier: 2
 visibility: internal
 cluster: worktree
 sub: status