npm - @event4u/agent-config - Versions diffs - 2.24.0 → 2.25.0 - Mend

@event4u/agent-config 2.24.0 → 2.25.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (51) hide show

package/.agent-src/commands/create-pr/description-only.md +39 -11
package/.agent-src/commands/create-pr.md +59 -5
package/.agent-src/commands/video/from-script.md +5 -5
package/.agent-src/commands/video/storyboard.md +1 -1
package/.agent-src/contexts/execution/roadmap-process-loop.md +69 -14
package/.agent-src/personas/README.md +3 -2
package/.agent-src/personas/ai-video-technical-director.md +2 -2
package/.agent-src/personas/hollywood-director.md +3 -3
package/.agent-src/profiles/content_creator.yml +5 -0
package/.agent-src/rules/media-governance-routing.md +82 -0
package/.agent-src/rules/persona-governance.md +90 -0
package/.agent-src/rules/post-push-rewrite-discipline.md +70 -0
package/.agent-src/rules/provider-lifecycle-discipline.md +75 -0
package/.agent-src/rules/roadmap-ci-steps-policy.md +145 -0
package/.agent-src/rules/roadmap-progress-sync.md +11 -5
package/.agent-src/skills/character-consistency/SKILL.md +12 -1
package/.agent-src/skills/git-workflow/SKILL.md +133 -0
package/.agent-src/skills/motion-choreographer/SKILL.md +12 -0
package/.agent-src/skills/pixar-storyteller/SKILL.md +19 -6
package/.agent-src/skills/roadmap-writing/SKILL.md +10 -0
package/.agent-src/skills/scene-expander/SKILL.md +22 -7
package/.agent-src/skills/video-director/SKILL.md +13 -0
package/.agent-src/templates/agents/agent-project-settings.example.yml +1 -1
package/.agent-src/templates/roadmaps.md +16 -0
package/.claude-plugin/marketplace.json +1 -1
package/CHANGELOG.md +43 -0
package/README.md +5 -3
package/config/agent-settings.template.yml +26 -0
package/docs/architecture.md +1 -1
package/docs/catalog.md +5 -2
package/docs/contracts/file-ownership-matrix.json +81 -13
package/docs/contracts/provider-lifecycle.md +122 -0
package/docs/decisions/ADR-011-domain-pack-readiness.md +213 -0
package/docs/decisions/INDEX.md +1 -0
package/docs/getting-started-by-role.md +10 -0
package/docs/getting-started.md +1 -1
package/docs/personas.md +73 -26
package/docs/profiles.md +9 -4
package/package.json +1 -1
package/scripts/_tmp_scan_framework_leakage.py +119 -0
package/scripts/ai-video/adapters/gemini-veo.sh +5 -0
package/scripts/ai-video/adapters/higgsfield.sh +6 -0
package/scripts/ai-video/adapters/kling.sh +5 -0
package/scripts/ai-video/adapters/openai-images.sh +5 -0
package/scripts/ai-video/adapters/sora.sh +6 -0
package/scripts/check_portability.py +6 -0
package/scripts/lint_media_policy_linkage.py +140 -0
package/scripts/lint_persona_governance.py +164 -0
package/scripts/lint_roadmap_ci_steps.py +182 -0
package/scripts/smoke/schema.sh +1 -1
package/.agent-src/personas/pixar-storyboard-artist.md +0 -98

package/.agent-src/commands/create-pr/description-only.md CHANGED Viewed

@@ -39,17 +39,45 @@ The user may or may not provide a PR URL or branch name.
    - If no PR found → use `git diff origin/{default}..HEAD --stat` for the branch diff.
 3. **Never** reuse a PR number from earlier in the conversation.
-### 2. Gather context
-- **Jira ticket**: Extract ticket ID from branch name (e.g. `fix/DEV-4673-description` → `DEV-4673`).
-  - If found → fetch via Jira API (`GET /issue/{ticketId}`).
-  - If not found → ask the user for a ticket number. Proceed without if none.
-- **Diff summary**: `git diff origin/{default}..HEAD --stat` for changed files.
-- **Commit messages**: `git log origin/{default}..HEAD --format="%s"` for what was done.
-- **PR template**: **MUST** read `.github/pull_request_template.md`. This is mandatory, not optional.
-- **Read key changed files** to understand what was done — look for migrations, new classes,
-  modified services, route changes, config changes.
-- **Check roadmap/agent docs** that describe the feature intent (if they exist).
+### 2. Gather context — **one parallel tool-call block**
+The four primary fetches below are **independent** and **must** be
+dispatched in a single parallel tool-call block, not serially. Serial
+reads here add 3+ round-trips per PR for zero benefit.
+```
+parallel:
+  1. Jira API           — GET /issue/{ticketId}   (skip when no ticket ID)
+  2. git diff           — git diff origin/{default}..HEAD --stat
+  3. git log            — git log origin/{default}..HEAD --format="%s"
+  4. view PR template   — .github/pull_request_template.md
+```
+After the block returns:
+- **Jira ticket**: ticket ID is extracted from the branch name
+  (e.g. `fix/DEV-4673-description` → `DEV-4673`) **before** the
+  parallel block. No ticket → skip fetch 1 silently; ask the user
+  for a number only after the block, and only if needed.
+- **PR template missing** → fall back to the structure in § 4.
+- **Read key changed files** (migrations, new classes, modified
+  services, route/config changes) — second parallel block, keyed
+  off the diff summary. Group all file reads in one block.
+- **Check roadmap/agent docs** that describe the feature intent
+  (if they exist) — fold into the second block.
+Anti-pattern (do **not** do this):
+```
+turn 1: fetch Jira
+turn 2: git diff
+turn 3: git log
+turn 4: view template
+turn 5: view file A
+turn 6: view file B
+```
+That's 6 round-trips for what should be 2.
 ### 3. Build the PR title

package/.agent-src/commands/create-pr.md CHANGED Viewed

@@ -94,6 +94,44 @@ Resolve `"draft"` (first match wins):
 3. `routine_confirmations: true` → ask `1. draft / 2. ready`.
 4. Default → `true` (silent draft).
+#### 3a. Tool selection — single-call mandate
+```
+POST THE PR WITH ONE github-api CALL.
+NEVER COMPOSE THE BODY THROUGH SHELL, PYTHON, OR TEMP FILES.
+```
+Use the `github-api` tool **directly** with the markdown body in the
+JSON `data` field. The body is a regular JSON string — escaping is the
+tool's job, not yours.
+```
+github-api
+  method: POST
+  path:   /repos/{owner}/{repo}/pulls
+  data:   { "title": "...", "body": "<markdown>", "head": "<branch>",
+            "base": "main", "draft": <bool> }
+```
+**Hard prohibitions** (each one cost 3+ extra tool calls in past runs):
+- ❌ `python3 -c "import urllib..."` / `python3 - <<PY ... PY` heredocs
+  to serialize the body or POST it.
+- ❌ `save-file PR_BODY.md` → read back → `curl -d @PR_BODY.md`.
+- ❌ `gh pr create --body-file …` shelling out when `github-api` is
+  available in this surface.
+- ❌ Splitting `title` and `body` into two API calls (create + PATCH).
+The body may contain any Markdown — code fences, tables, multi-line
+HTML, emoji. Do **not** preprocess, escape, or strip newlines before
+handing it to `github-api`.
+If the surface genuinely lacks `github-api` (rare), fall back to
+`gh pr create --title "..." --body-file <(echo -n "<body>")` as a
+**single** shell call, never the python-urllib path.
+#### 3b. Submit
 Create the PR with the approved title/body and the resolved `draft`.
 **Verify after `draft: false`** — the GitHub REST API sometimes ignores
@@ -126,18 +164,21 @@ Run this strip-pass **after PR creation and after every body PATCH**:
    - `Pull Request opened by [Augment Code]`
    - `Co-authored by Augment Code`
    - Any `augmentcode.com` link the user did not ask for
-3. If any pattern is present, remove it together with surrounding
+3. **No match → done.** Skip steps 4–5; the body is already clean.
+   This is the common path and **must not** spend a verify-GET.
+4. Match found → remove the footer(s) together with surrounding
    `---` separators and trailing whitespace, then:
    ```
    PATCH /repos/{owner}/{repo}/pulls/{number}
    { "body": "<cleaned body>" }
    ```
-4. Re-fetch the body once more to verify the strip stuck. If a
-   pattern reappears (server re-injection), repeat steps 2–4 once;
+   Re-fetch the body **once** to verify the strip stuck. If a
+   pattern reappears (server re-injection), repeat the PATCH once;
    if it still reappears, surface the issue to the user and stop
    (do not enter a strip/PATCH loop).
-5. Briefly note in the reply how many footers were removed (or
-   "no footers found" if clean).
+5. Briefly note in the reply how many footers were removed (omit
+   the line entirely when nothing was stripped — silence is the
+   expected path, not "no footers found").
 #### 4b. Show the PR URL (verbosity-gated)
@@ -154,6 +195,19 @@ Linked ticket + `routine_confirmations: true` → ask `1. Yes / 2. No`.
 Default (`false`) → skip silently. **Only emit a transition line when
 an actual Jira API call succeeded** — never announce "skipped".
+#### 4d. Settings short-circuit — single read per run
+`verbosity.routine_confirmations`, `verbosity.post_action_reports`, and
+`commands.create_pr.preview_description` are read **once** at the top
+of the run and cached for the whole `/create-pr` invocation. Do **not**
+re-read `.agent-settings.yml` in 4b / 4c — both branches resolve from
+the cached values from step 1.
+When all three resolve to their silent defaults (`false` / `minimal` /
+`false`), steps 4b–4c collapse to the single `→ #N opened: <url>` line
+from 4b and a silent 4c. No extra file reads, no "checking settings…"
+narration, no confirmation prompts.
 ### Rules
 - **Always use the PR template** from `.github/pull_request_template.md`.

package/.agent-src/commands/video/from-script.md CHANGED Viewed

@@ -5,7 +5,7 @@ cluster: video
 sub: from-script
 description: Drive a script end-to-end through the AI video pipeline — scenes → blueprint → image → operator pick → motion → video → stitch. Dry-run default; network calls require explicit per-turn confirmation.
 disable-model-invocation: true
-personas: [hollywood-director, ai-video-technical-director, pixar-storyboard-artist]
+personas: [hollywood-director, ai-video-technical-director]
 skills: [scene-expander, video-director, pixar-storyteller, character-consistency, motion-choreographer]
 suggestion:
   eligible: true
@@ -19,7 +19,7 @@ suggestion:
 Drives a Markdown script through the full pipeline. Provider flags
 override the `<default-image-provider>` / `<default-video-provider>`
-from [`agents/.ai-video.xml`](../../agents/.ai-video.xml.example);
+from [`agents/.ai-video.xml`](../../../agents/.ai-video.xml.example);
 absent flags fall back to the XML defaults.
 **Block-on-ambiguity:** a missing scene heading, an unparseable
@@ -49,7 +49,7 @@ provider in this order: command flag → `agents/.ai-video.xml` default
 Run the `scene-expander` skill: split on `## Scene N` headings, extract
 dialogue / action / ambient blocks, and emit one `scene-blueprint.yaml`
 per scene under `<project>/scenes/<id>/`. Schema:
-[`scene-blueprint.schema.yaml`](../skills/scene-expander/scene-blueprint.schema.yaml).
+[`scene-blueprint.schema.yaml`](../../skills/scene-expander/scene-blueprint.schema.yaml).
 ### 4. Character lock
@@ -66,7 +66,7 @@ For each scene blueprint:
 2. **Safety gate (Phase 5 Step 6).** If `AIV_DRYRUN=false`, print the
    adapter, model, scene count, and estimated cost; refuse to continue
    without an explicit operator confirmation **in this turn**. Mirrors
-   [`non-destructive-by-default`](../rules/non-destructive-by-default.md).
+   [`non-destructive-by-default`](../../rules/non-destructive-by-default.md).
 3. Call the image adapter (`run` subcommand) N times where N =
    `<tuning/best-of-n>` (default 1).
@@ -120,4 +120,4 @@ estimated cost (live mode) or `dry-run` marker. No commit. No push.
 - [`/video:scene`](scene.md) — single-scene iteration
 - [`/video:storyboard`](storyboard.md) — image-only contact sheet
 - [`/video:stitch`](stitch.md) — re-stitch after operator edits
-- [`scripts/ai-video/lib/adapter-contract.md`](../../scripts/ai-video/lib/adapter-contract.md)
+- [`scripts/ai-video/lib/adapter-contract.md`](../../../scripts/ai-video/lib/adapter-contract.md)

package/.agent-src/commands/video/storyboard.md CHANGED Viewed

@@ -5,7 +5,7 @@ cluster: video
 sub: storyboard
 description: Image-only storyboard — script → scenes → blueprint → image render → contact-sheet PNG via ffmpeg montage. No video calls.
 disable-model-invocation: true
-personas: [hollywood-director, pixar-storyboard-artist]
+personas: [hollywood-director]
 skills: [scene-expander, video-director, character-consistency]
 suggestion:
   eligible: true

package/.agent-src/contexts/execution/roadmap-process-loop.md CHANGED Viewed

@@ -61,9 +61,12 @@ matching `commit:` / `git commit` / `Commit phase` patterns).
 - **Commit steps present, non-autonomous** → ask before each commit
   step inside the loop.
-## 4. Resolve quality cadence
+## 4. Resolve cadences — read once, cache for the run
-Read `roadmap.quality_cadence` from `.agent-settings.yml` once:
+Read both keys from `.agent-settings.yml` once and cache for the whole
+run. Do **not** re-read inside the step loop.
+**`roadmap.quality_cadence`** — when to run the quality pipeline:
 | Value | Pipeline runs |
 |---|---|
@@ -75,28 +78,80 @@ Missing / unreadable / unknown → fall back to `end_of_roadmap`.
 The Iron Law [`verify-before-complete`](../../rules/verify-before-complete.md)
 still mandates fresh quality output before any "complete" claim.
+**`roadmap.dashboard_regen_cadence`** — when to run the dashboard
+subprocess between steps:
+| Value | `./agent-config roadmap:progress` runs |
+|---|---|
+| `per_step` (default) | After every checkbox flip |
+| `every_5_steps` | Every 5th closed step + at phase boundary + at reply end |
+| `phase_boundary` | Only at phase boundaries + run end |
+`process-step` ignores this — single-step runs always regen at step
+end. Any file-shape touch (rename / phase add / archive — Iron Law 1
+of [`roadmap-progress-sync`](../../rules/roadmap-progress-sync.md))
+forces an immediate regen regardless of cadence. The checkbox flip
+itself is **never** batchable — only the subprocess.
 ## 5. Step loop
 For each open step in the working set (scope-bound — see wrapper):
-1. Read the step description and inline notes.
+0. **CI-step gate** — per
+   [`roadmap-ci-steps-policy`](../../rules/roadmap-ci-steps-policy.md).
+   When `quality.local_auto_run: false` and the step text matches a
+   CI-shaped literal (`task ci`, `task ci-fast`, `task ci-strict`,
+   `make ci`, `make test`, `npm/pnpm run check`, `yarn check`,
+   `composer test`, whole-suite `vendor/bin/phpunit`, whole-suite
+   `php artisan test`) **without** an inline
+   `<!-- carve-out: new-gate-verification -->` marker → flip the
+   checkbox to `[-]`, append
+   `<!-- skipped: quality.local_auto_run=false → remote CI is the gate -->`
+   on the same line, regenerate the dashboard, continue to the next
+   step. Never run the gate. Carve-out marker present → run normally
+   (new gate must be verified once locally). Setting `true` → run
+   normally.
+1. **Bundled read — one parallel tool-call block.** The step
+   description, the immediately-relevant code files, and any
+   guideline/context the step cites are **independent** reads and
+   **must** be dispatched together, not serially.
+   ```
+   parallel:
+     - view agents/roadmaps/<file>.md     (the step's section)
+     - view <files cited in the step text>
+     - codebase-retrieval (only if the step is vague)
+   ```
+   Anti-pattern: `view step` → think → `view file A` → think →
+   `view file B`. That's 3 round-trips for what should be 1.
 2. Analyze the codebase for what the step requires.
 3. Decide and act — implement. **No "should I implement this?" prompt.**
 4. **Open question handling:**
    - **Council on** → invoke per [`ai-council`](../../skills/ai-council/SKILL.md),
      integrate convergence, proceed. Token spend was opted in.
    - **Council off** → halt, surface once, wait. Resume on next turn.
-5. **Atomic flip + regen** — before moving to step N+1, in the **same
-   reply** that landed step N's work:
-   1. Flip the checkbox in `agents/roadmaps/<file>.md`: `[x]` done ·
-      `[~]` partial · `[-]` skipped.
-   2. Run `./agent-config roadmap:progress` to regenerate the
-      dashboard.
-   This pair is **non-skippable** and **non-batchable** per Iron Law 2
-   of [`roadmap-progress-sync`](../../rules/roadmap-progress-sync.md). A
-   loop iteration that lands work without flipping its box is a rule
-   violation. Do not save flips for the archive commit.
-6. Run quality pipeline if cadence is `per_step`.
+5. **Atomic flip — same reply, every step.**
+   Flip the checkbox in `agents/roadmaps/<file>.md`: `[x]` done ·
+   `[~]` partial · `[-]` skipped. **Non-skippable, non-batchable**
+   per Iron Law 2 of
+   [`roadmap-progress-sync`](../../rules/roadmap-progress-sync.md).
+   A loop iteration that lands work without flipping its box is a
+   rule violation. Do not save flips for the archive commit.
+6. **Dashboard regen — cadence-gated.** Run
+   `./agent-config roadmap:progress` when due per
+   `roadmap.dashboard_regen_cadence` (resolved in § 4):
+   - `per_step` → always after the flip.
+   - `every_5_steps` → after the 5th, 10th, … closed step **of this
+     run**, or when the reply ends with closed steps pending regen.
+   - `phase_boundary` → skip; the boundary handler in § 5 wrapper /
+     § 6 runs the regen.
+   - Any file-shape touch (rename / phase add / archive — Iron Law 1)
+     → run immediately regardless of cadence.
+   Skipped regens accumulate into the next due regen — the markdown
+   file is the source of truth between regens.
+7. Run quality pipeline if cadence is `per_step`.
 ### Halt conditions

package/.agent-src/personas/README.md CHANGED Viewed

@@ -63,11 +63,12 @@ the linter check list.
 |---|---|---|
 | `qa` | specialist | testability, failure scenarios |
 | `hollywood-director` | specialist | live-action cinematic prompts — lens, lighting, blocking, negative constraints |
-| `pixar-storyboard-artist` | specialist | animation acting — emotional beat, want / obstacle, environment reaction |
 | `ai-video-technical-director` | specialist | provider tuning — Veo / Kling / OpenAI / Higgsfield / Sora grammar, token caps, audio flags |
 More specialists may land in v1.1+ — each must pass the
-Unique-Questions heuristic before being drafted.
+Unique-Questions heuristic before being drafted. Removed personas
+are deleted in-commit (no soak window) per
+[`persona-governance § Deprecation path`](../rules/persona-governance.md).
 ## How skills use personas

package/.agent-src/personas/ai-video-technical-director.md CHANGED Viewed

@@ -18,7 +18,7 @@ audio capability. Refuses one-prompt-fits-all; demands a tuned variant
 per adapter. Catches prompts that would silently truncate, fall back
 to a default aspect, or drop audio on a video-only model. Not
 responsible for camera grammar (`hollywood-director`) or acting
-(`pixar-storyboard-artist`).
+(`pixar-storyteller` skill).
 ## Mindset
@@ -77,5 +77,5 @@ count.
 ## Composes well with
 - `hollywood-director` — consumes the 11-block prompt; folds it into provider grammar.
-- `pixar-storyboard-artist` — consumes the four-block storyboard; preserves beat counts in MOTION PROMPT.
+- `pixar-storyteller` skill — consumes the four-block storyboard; preserves beat counts in MOTION PROMPT.
 - `motion-choreographer` skill — drafts per-provider motion + audio directions against this output.

package/.agent-src/personas/hollywood-director.md CHANGED Viewed

@@ -17,7 +17,7 @@ lens, the light, the camera move, blocking, and negative constraints
 are all on the page. Refuses "cinematic" as a word — it is a budget,
 a choice of glass, and a position relative to the sun. Catches shots
 still readable as stock footage. Not responsible for animation pacing
-(`pixar-storyboard-artist`) or provider tokens (`ai-video-technical-director`).
+(`pixar-storyteller` skill) or provider tokens (`ai-video-technical-director`).
 ## Mindset
@@ -92,8 +92,8 @@ declarative sentence — no adjective stacks, no "ultra-realistic".
 ## Composes well with
-- `pixar-storyboard-artist` — when the beat is emotional rather than
-  procedural; the storyboard artist names the acting, this persona
+- `pixar-storyteller` skill — when the beat is emotional rather than
+  procedural; the storyteller skill names the acting, this persona
   names the camera around it.
 - `ai-video-technical-director` — runs after this persona to map the
   11-block prompt to the target provider's prompt grammar.

package/.agent-src/profiles/content_creator.yml CHANGED Viewed

@@ -16,10 +16,15 @@ profile:
       - editorial-calendar
       - release-comms
       - prompt-engineering-patterns
+      - character-consistency
   surface:
     commands_hint:
       - work
       - post-as
       - ghostwriter
       - optimize-prompt
+      - video:from-script
+      - video:storyboard
+      - video:scene
+      - video:stitch
     docs_first_pointer: "docs/getting-started-by-role.md#content_creator"

package/.agent-src/rules/media-governance-routing.md ADDED Viewed

@@ -0,0 +1,82 @@
+---
+type: "auto"
+tier: "2a"
+description: "When generating AI video/image/voice — surface project-local media policies (likeness, style, public-figures, voice-cloning, disclosure)"
+source: package
+triggers:
+  - keyword: "/video:"
+  - keyword: "/image:"
+  - keyword: "/audio:"
+  - keyword: "deepfake"
+  - keyword: "voice clone"
+  - keyword: "voice cloning"
+  - keyword: "likeness"
+  - keyword: "brand impersonation"
+  - phrase: "in the style of"
+  - phrase: "in the voice of"
+  - phrase: "as [public figure]"
+  - phrase: "impersonate"
+applies_to_user_types:
+  - "creator"
+  - "marketing"
+  - "gtm"
+validator_ignore:
+  - type: "substring"
+    pattern: "../../agents/"
+    reason: "Routing rule whose subject matter is the project-local agents/policies/media/ tree; every body link points there by design."
+  - type: "substring"
+    pattern: ".agent-src.uncompressed/"
+    reason: "Rule contrasts project-local placement with the .agent-src.uncompressed/rules/ alternative — mentioning the path is the argument."
+---
+# Media Governance Routing
+## Iron Law
+```
+WHEN AI VIDEO, IMAGE, OR VOICE GENERATION FIRES, CONSULT THE PROJECT-LOCAL
+MEDIA POLICIES IN agents/policies/media/ BEFORE EMITTING THE PROMPT TO
+THE PROVIDER. REFUSE-AND-SURFACE OVER GUESS-AND-RENDER.
+```
+Routes agent to project-local media governance policy layer at [`agents/policies/media/`](../../agents/policies/media/) when video / image / voice surface fires. Policies are LLM-readable decision frameworks consulted in-session, not Python-enforced gates — see [`agents/policies/media/README.md § Enforcement model`](../../agents/policies/media/README.md) for full agent-in-the-loop contract.
+## What this rule surfaces
+Any trigger match → agent loads into context:
+- [`agents/policies/media/likeness.md`](../../agents/policies/media/likeness.md) — real person's visual likeness.
+- [`agents/policies/media/style.md`](../../agents/policies/media/style.md) — named living artist's distinctive style.
+- [`agents/policies/media/public-figures.md`](../../agents/policies/media/public-figures.md) — recognised public figures.
+- [`agents/policies/media/voice-cloning.md`](../../agents/policies/media/voice-cloning.md) — vocal likeness.
+- [`agents/policies/media/disclosure.md`](../../agents/policies/media/disclosure.md) — mandatory non-removable AI-generation disclosure.
+- [`agents/policies/media/brand-impersonation.md`](../../agents/policies/media/brand-impersonation.md) — brand / broadcaster identity imitation.
+- [`agents/policies/media/transparency.md`](../../agents/policies/media/transparency.md) — provenance metadata (C2PA, SynthID).
+Each policy carries own trigger block → within active context agent narrows from superset to policies whose specific patterns actually fired (e.g. prompt naming public figure → `public-figures.md` + `disclosure.md`; `--no-disclosure` → `disclosure.md` standalone).
+## Why project-local, not `.agent-src.uncompressed/rules/`
+Seven media policies live under [`agents/policies/media/`](../../agents/policies/media/), not as `.agent-src.uncompressed/rules/domain-safety-media-*.md`, for three reasons:
+1. **Consumed by skills + adapters**, not surfaced as standalone always-loaded prose. Cost non-trivial (7 × ~80 lines = ~560 lines always-context if hoisted to rules), and most sessions never touch video / image / voice surface.
+2. **Enforcement model project-local** — working precedent (`/ghostwriter:*` mandatory footer in `write-engine.md`) + audit log (session transcripts) are project artifacts. Rules under `.agent-src.uncompressed/` are tool-portable governance; these policies are domain-specific bindings.
+3. **Extraction to reusable domain pack explicitly deferred** until second non-video domain (audio, image, docs, exports) lands with overlapping execution surfaces. Until then, one-domain abstraction structurally premature — policies stay project-local, routing rule on-demand bridge.
+This routing rule is the bridge: sits in always-loaded rule set so trigger keywords surface project-local policies into context on demand, without paying full always-loaded cost.
+## CI reachability guarantee
+[`scripts/lint_media_policy_linkage.py`](../../scripts/lint_media_policy_linkage.py) fails build if any policy file under `agents/policies/media/` not linked from:
+- this routing rule, **or**
+- a skill's `## Policies` see-also block, **or**
+- another policy file's `## See also` block.
+Policy that no skill, rule, or sibling policy references → silent policy. CI check is structural reachability guarantee that agent-in-the-loop model rests on.
+## See also
+- [`agents/policies/media/README.md`](../../agents/policies/media/README.md) — full enforcement-model contract.
+- [`.augment/rules/ask-when-uncertain.md`](../../.augment/rules/ask-when-uncertain.md) — single-question refusal-path discipline every policy depends on.
+- [`docs/contracts/write-engine.md`](../docs/contracts/write-engine.md) — prose-disclosure precedent extended to media by [`disclosure.md`](../../agents/policies/media/disclosure.md).

package/.agent-src/rules/persona-governance.md ADDED Viewed

@@ -0,0 +1,90 @@
+---
+type: "auto"
+tier: "2a"
+description: "When creating, editing, or proposing personas — enforce per-domain cap (≤ 2 specialists), ≥ 1 skill citation, and the deprecation path"
+source: package
+triggers:
+  - path_prefix: ".agent-src.uncompressed/personas/"
+  - path_prefix: ".agent-src/personas/"
+  - keyword: "persona"
+  - keyword: "personas"
+  - phrase: "new persona"
+  - phrase: "add a persona"
+  - phrase: "specialist persona"
+  - phrase: "review lens"
+routes_to:
+  - "contract:persona-schema"
+applies_to_user_types:
+  - "maintainer"
+  - "developer"
+validator_ignore:
+  - type: "substring"
+    pattern: "../../docs/"
+    reason: "Rule routes to docs/contracts/persona-schema.md and docs/personas.md — the canonical persona catalog and schema live there by design."
+  - type: "substring"
+    pattern: ".agent-src.uncompressed/"
+    reason: "Rule documents the persona authoring tree (.agent-src.uncompressed/personas/) as the deprecation-path operand."
+---
+# Persona Governance
+## Iron Law
+```
+ONE PERSONA, ONE OWNER, ONE SKILL CITATION, ONE DOMAIN SLOT.
+NO NEW SPECIALIST WITHOUT A DEPRECATION CANDIDATE WHEN THE DOMAIN IS FULL.
+```
+Personas are review lenses, not free real estate. Every specialist persona has a maintenance cost: it must stay aligned with the schema, the cited skills must still want it, and the per-domain reasoning surface must not bloat to the point that no single persona is load-bearing. This rule routes the agent to [`docs/contracts/persona-schema.md`](../docs/contracts/persona-schema.md) and [`docs/personas.md`](../../docs/personas.md) and enforces the four discipline checks below.
+## The four checks
+### 1. Per-domain cap — ≤ 2 specialised personas per content domain
+A **content domain** is a self-contained creative or technical surface that one or two specialist personas can fully cover. Current domains:
+| Domain | Specialists allowed | Examples |
+|---|---|---|
+| ai-video / ai-image / ai-audio | ≤ 2 | one director-shaped lens + one technical-tuning lens |
+| backend engineering | ≤ 2 | architect + ORM-tamer |
+| frontend engineering | ≤ 2 | component / lifecycle + design / a11y |
+| security | ≤ 2 | abuse-case + secrets-and-trust |
+| gtm / growth | ≤ 2 | CMO + RevOps |
+| money / strategy | ≤ 2 | finance-partner + strategist |
+| people / org | ≤ 2 | engineering-manager + people-strategist |
+| customer / discovery | ≤ 2 | discovery-lead + customer-success-lead |
+**Core personas** (`developer`, `senior-engineer`, `product-owner`, `stakeholder`, `critical-challenger`, `ai-agent`) are exempt — they are always-loaded cross-cutting lenses, not domain specialists.
+A new specialist into a full domain MUST come with a deprecation candidate from the same domain. The agent surfaces both, then runs an ai-council debate (per [`ai-council`](../../.agent-src/skills/ai-council/SKILL.md)) before any rename / merge / delete.
+### 2. Skill citation floor — ≥ 1 cite before merge
+A specialist persona without a `personas: [<id>]` citation in at least one skill's frontmatter is dead weight. The PR adding the persona MUST also add the citation, OR the PR is rejected. Citation map lives in [`docs/personas.md § Skill citations`](../../docs/personas.md#skill-citations).
+### 3. Deprecation path — delete immediately, record in commit
+A persona being removed is **deleted in the same commit** that lands its replacement. The commit message names the successor (or "merged into X") and cites the council decision (or maintainer rationale) that authorised it. No soak window — internal personas have no external consumers; a persona file kept around as a tombstone is dead weight the linter still loads. No silent deletes either: the audit trail is the commit, not a docs table.
+### 4. Schema conformance — the skill linter is the gate
+Every persona file is linted against [`docs/contracts/persona-schema.md`](../docs/contracts/persona-schema.md) by the skill linter: frontmatter shape, tier enum, wing enum, required sections per tier, line budget per tier (with wing override), `Unique Questions` ≥ 3, filename / id match, description ≤ 160 chars. The agent runs `python3 scripts/skill_linter.py` before any persona PR is marked ready.
+## Failure modes — what counts as a violation
+- Adding a third specialist to a full domain without naming the deprecation candidate.
+- Landing a specialist with no `personas: [<id>]` cite in any skill.
+- Renaming or deleting a persona file without naming the successor (or sunset reason) in the commit message.
+- Editing core-tier personas in-place with breaking changes (rename, section removal) without bumping to a new id.
+- Skipping the skill linter (`python3 scripts/skill_linter.py`) on a persona PR.
+## Day-one state
+Resolved 2026-05-17 via two-round ai-council debate (members: anthropic/claude-sonnet-4-5, openai/gpt-4o — converged delete-and-fold): `pixar-storyboard-artist` deleted; acting / beat-decomposition lens folded into [`pixar-storyteller`](../skills/pixar-storyteller/SKILL.md) skill body. Active per-domain count for `ai-video` now 2 (`ai-video-technical-director`, `hollywood-director`), within cap. Total active personas in root cluster: 24 (plus 5 advisors in `personas/advisors/`). Full inventory + ownership in [`docs/personas.md`](../../docs/personas.md).
+## See also
+- [`docs/contracts/persona-schema.md`](../docs/contracts/persona-schema.md) — schema lock, tiers, sections, size budgets, linter enforcement surface.
+- [`docs/personas.md`](../../docs/personas.md) — active persona catalog, citation map, ownership column.
+- [`ai-council`](../../.agent-src/skills/ai-council/SKILL.md) — neutral second-opinion mechanism used for merge / deprecation decisions.
+- [`skill-quality`](skill-quality.md) — sibling discipline rule for skill files.

package/.agent-src/rules/post-push-rewrite-discipline.md ADDED Viewed

@@ -0,0 +1,70 @@
+---
+type: "auto"
+tier: "2a"
+alwaysApply: false
+description: "Git history after a push — squash/amend/rebase of pushed commits must pair with immediate re-push in same turn; stop on divergent state"
+source: package
+triggers:
+  - intent: "squash the pushed branch"
+  - intent: "clean up commits on the PR branch"
+  - intent: "tidy history after pushing"
+  - keyword: "git rebase -i"
+  - keyword: "--amend"
+  - keyword: "force-push"
+  - keyword: "--force-with-lease"
+  - phrase: "branch diverged"
+  - phrase: "pull --rebase failed"
+  - phrase: "ahead and behind"
+routes_to:
+  - "skill:git-workflow"
+---
+# Post-Push Rewrite Discipline
+## Iron Law
+```
+ONCE PUSHED, A COMMIT IS PUBLISHED.
+ANY REWRITE OF PUSHED HISTORY MUST PAIR WITH AN IMMEDIATE RE-PUSH
+IN THE SAME TURN — OR DON'T REWRITE.
+NEVER END A SESSION WITH REWRITTEN-BUT-UNPUSHED LOCAL HISTORY.
+```
+## Two protective stops
+1. **Pre-rewrite stop.** Before any squash / amend / rebase on a
+   branch that is on origin: `git fetch && git rev-list --left-right
+   --count HEAD...@{u}`. If **either** side is non-zero — STOP and
+   route to `skill:git-workflow § Divergent-State Recovery`. A blind
+   `git pull --rebase` in this state is the documented failure mode.
+2. **Post-rewrite stop.** After the rewrite, push in the **same turn**
+   with `--force-with-lease=<branch>:<fetched-sha>` and verify
+   `git rev-parse origin/<branch>` equals `git rev-parse HEAD`.
+   If the push fails (hook, network, token budget) — fix the cause
+   and re-push **before** ending the session, committing new work,
+   or handing off.
+If either stop fires and resolution is not immediate → tag the state
+(`git tag local-rewritten-tip-<ISO-date>`) and hand control back to
+the user. Do not let a new session inherit a dirty divergence.
+## Why this rule exists
+A previous session squashed a pushed branch, the push hook failed at
+the token boundary, the session ended — and the next session saw
+local and origin pointing at different SHAs for the same logical work.
+A blind `git pull --rebase` cascaded into conflicts across every
+derived file (`.compression-hashes.json`, router projections). Recovery
+required forensic SHA-archaeology. This rule makes that sequence
+structurally impossible: rewrite without immediate push is forbidden.
+## See also
+- [`no-unsolicited-rebase`](no-unsolicited-rebase.md) — whether to
+  rewrite at all (this rule kicks in once rewriting is authorized).
+- [`skill:git-workflow`](../skills/git-workflow/SKILL.md) — Safe
+  Squash-After-Push protocol and Divergent-State Recovery decision
+  tree.
+- [`commit-policy`](commit-policy.md) — never rewrite or commit
+  without explicit authorization.