@event4u/agent-config 2.23.0 → 2.25.0

package/.agent-src/skills/pixar-storyteller/SKILL.md

@@ -0,0 +1,120 @@
+---
+name: pixar-storyteller
+description: "Use when turning an idea into a Pixar-style animation prompt — character sheet, scene, image, video — anchored in emotional beat, want, obstacle. Triggers 'Pixar prompt', 'animated scene'."
+source: package
+domain: product
+---
+
+# pixar-storyteller
+
+> Turn an animation beat into the **four-block storyboard**:
+> CHARACTER SHEET · SCENE PROMPT · IMAGE PROMPT · VIDEO PROMPT.
+> Output is provider-agnostic; provider tuning is
+> [`motion-choreographer`](../motion-choreographer/SKILL.md).
+>
+> The acting / storyboard lens is enforced inline by the procedure
+> and self-review below.
+
+## When to use
+
+- A scene is animated / stylized (not photoreal) and needs an
+  emotional read, not a film-set read.
+- The character must want something and the environment must
+  respond — flat poses fail.
+- Live-action / photoreal beats → [`video-director`](../video-director/SKILL.md).
+
+Do NOT use when:
+
+- The deliverable is provider-tuned token grammar →
+  `motion-choreographer` after this skill.
+- A character must be re-used across scenes → run
+  [`character-consistency`](../character-consistency/SKILL.md) first
+  to lock the CHARACTER SHEET, then call this skill.
+- The brief is a static graphic / poster → `canvas-design`.
+
+## Procedure
+
+### Step 0: Inspect
+
+1. Confirm the input is an animated / stylized beat.
+2. If `character.json` exists under `agents/ai-video/<project>/characters/`,
+   read identity tokens — reused verbatim in CHARACTER SHEET.
+3. Read the beat once. Name the *want* and the *obstacle* in one
+   sentence each before drafting.
+
+### Step 1: Draft the four blocks
+
+Emit each block under a labeled heading. Blocks are mandatory and
+in this order:
+
+1. **CHARACTER SHEET** — silhouette, palette, wardrobe, signature
+   prop, posture default, eye behavior. Verbatim from `character.json`
+   when a lock exists.
+2. **SCENE PROMPT** — single emotional beat, want, obstacle,
+   stylistic anchor (specific film + year — "Up (2009)", not
+   "Pixar-style"), environment reaction.
+3. **IMAGE PROMPT** — one still at the peak of the beat. Names
+   composition, eye line, palette. No motion verbs.
+4. **VIDEO PROMPT** — decomposes the moment into
+   `anticipation Xs · action Ys · reaction Zs` with explicit beat
+   counts. Names which secondary motion (hair, cloth, dust) reacts
+   on which beat.
+
+### Step 2: Self-review
+
+1. Exactly one emotional beat in SCENE PROMPT? Compound moods fail.
+2. Stylistic anchor is a specific film + year? Generic style → fail.
+3. VIDEO PROMPT names beat counts per phase?
+4. IMAGE PROMPT names eye line?
+5. CHARACTER SHEET matches `character.json` byte-for-byte when a
+   lock exists?
+
+Any "no" → revise that block.
+
+### Step 3: Validate
+
+1. Output is plain text, one labeled block per heading, ready for
+   `scripts/ai-video/lib/parse-blueprint.sh`.
+2. No provider tokens — that is `motion-choreographer`.
+3. No lens / focal-length prescriptions — that is `video-director`'s
+   block, not this one.
+
+## Output format
+
+1. **`scenes/<id>/prompt.txt`** — four labeled blocks, ready for
+   the blueprint parser.
+2. **`scenes/<id>/review.md`** — one-paragraph rationale per
+   non-obvious choice (stylistic anchor, environment reaction,
+   beat decomposition).
+
+## Gotcha
+
+- The model defaults to "Pixar-style" with no film anchor — that
+  reads as a wishlist. Force a specific title + year.
+- Neutral faces are the AI default — every beat names a feeling
+  the face is doing, including eye line direction.
+- Environment-as-backdrop is the silent failure mode — name what
+  the world *does* in response to the character.
+- Collapsing anticipation and action into one verb makes motion
+  look teleported. Both phases or the prompt fails review.
+- When `character.json` exists, paraphrasing breaks Character Lock —
+  copy identity tokens verbatim.
+
+## Do NOT
+
+- Do NOT prescribe lenses or focal lengths — that is `video-director`.
+- Do NOT emit provider-specific tokens — that is `motion-choreographer`.
+- Do NOT cite "Pixar-style" without a specific film + year.
+- Do NOT compound emotional beats ("sad but hopeful and tired").
+
+## Policies
+
+The Pixar-storyteller skill anchors prompts to named films and studios by design — the policy surface is the largest in the video cluster:
+
+- [`agents/policies/media/style.md`](../../../agents/policies/media/style.md) — naming a film + year as the *primary* anchor crosses the "in the style of [STUDIO]" trigger; surface and refuse without a transformative-intent rationale.
+- [`agents/policies/media/likeness.md`](../../../agents/policies/media/likeness.md) — when a beat references a named animator's signature character (real-person extension of style).
+- [`agents/policies/media/public-figures.md`](../../../agents/policies/media/public-figures.md) — when the storyteller's character is a recognised public figure rendered in Pixar shape.
+- [`agents/policies/media/disclosure.md`](../../../agents/policies/media/disclosure.md) — every Pixar-style output ships with the AI-generation disclosure; parody / commentary cases are flagged for human review.
+
+Refuse-and-surface when style ⇒ primary signature, not one influence among several.
+

package/.agent-src/skills/roadmap-writing/SKILL.md

@@ -137,6 +137,16 @@ to every roadmap you author.
   user (`commit-policy` Iron Law). A roadmap is "implementation-complete"
   once its checkboxes are ticked and verification has been run — merge
   timing is tracked outside the roadmap.
+* Schedule full-pipeline CI literals (`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`) as checkbox steps when
+  `quality.local_auto_run: false` — blocked by
+  `task lint-roadmap-ci-steps` per
+  [`roadmap-ci-steps-policy`](../../rules/roadmap-ci-steps-policy.md).
+  Reword as narrow verifications, or mark with
+  `<!-- carve-out: new-gate-verification -->` when it verifies a NEW
+  gate this roadmap introduces.
 * Use ALL-CAPS Iron-Law fenced blocks — those belong in
   [`kernel-membership`](../../../docs/contracts/kernel-membership.md)-listed
   rules, not roadmaps.

package/.agent-src/skills/scene-expander/SKILL.md

@@ -0,0 +1,137 @@
+---
+name: scene-expander
+description: "Use when expanding a one-line idea into the 12-block Cinematic Scene Blueprint — provider-agnostic, includes optional dialogue + ambient. Triggers 'expand this scene', 'blueprint for X'."
+personas:
+  - hollywood-director
+source: package
+domain: product
+---
+
+# scene-expander
+
+> Expand a one-line idea or script line into the **Cinematic Scene
+> Blueprint** — 12 labeled blocks consumed by
+> [`parse-blueprint.sh`](./scene-blueprint.schema.yaml). Picks
+> `hollywood-director` for live-action; hands off animated beats to
+> [`pixar-storyteller`](../pixar-storyteller/SKILL.md). Output is
+> provider-agnostic — provider tuning is
+> [`motion-choreographer`](../motion-choreographer/SKILL.md).
+
+## When to use
+
+- A script line, idea, or beat needs a full blueprint before any
+  adapter runs.
+- A `/video:from-script` run is parsing `## Scene N` headings and
+  needs each scene expanded.
+
+Do NOT use when:
+
+- The brief is already an 11-block cinematic prompt → call
+  `video-director` directly to refine it.
+- The brief is a static graphic → `canvas-design`.
+- Provider-specific token tuning is the next step →
+  `motion-choreographer`.
+
+## Procedure
+
+### Step 0: Inspect
+
+1. Read the input line. Classify as **live-action / photoreal** or
+   **animated / stylized**.
+2. Live-action → load `hollywood-director` voice. Animated → hand
+   off to [`pixar-storyteller`](../pixar-storyteller/SKILL.md) (its
+   procedure carries the acting / beat-decomposition lens). Hybrid
+   (live-action with VFX) → `hollywood-director`; record VFX intent
+   in ENVIRONMENT.
+3. Check for an existing `character.json` lock under
+   `agents/ai-video/<project>/characters/`.
+
+### Step 1: Emit the 12 blocks
+
+One label per line. Order is mandatory.
+
+1. **STYLE** — stylistic anchor (live-action: film stock + decade,
+   e.g. "Kodak 5219, 2015"; animated: specific film + year).
+2. **SUBJECT** — character read; verbatim identity tokens when a
+   lock exists.
+3. **ENVIRONMENT** — location, time-of-day, weather, era; what the
+   world does in response to the subject.
+4. **ACTION** — anticipation / action / reaction with beat counts
+   (`0.5s / 1.2s / 0.8s`). No adjective paragraphs.
+5. **CAMERA** — position, height, distance, move (lock-off, dolly,
+   handheld, push, pull). Off-axis when on-axis is default.
+6. **LENS** — focal length in mm and aperture intent. "Cinematic"
+   alone fails.
+7. **LIGHTING** — key / fill / back / practical named; "golden
+   hour" requires a sun angle.
+8. **MOOD** — one emotional read.
+9. **DIALOGUE** — optional. If present: `speaker: "line"`, one per
+   line. Marks `audio: native` capability requirement.
+10. **AMBIENT SOUND** — optional. Layer list (wind, traffic,
+    crowd, ocean). Marks `audio: native` or routes to ffmpeg mux.
+11. **DURATION** — seconds (integer or one decimal).
+12. **NEGATIVE** — clichés to reject, load-bearing order top-first.
+    Always names: centered framing, symmetric composition, generic
+    "cinematic", soap-opera contrast.
+
+### Step 2: Self-review
+
+1. Live-action / animated classification consistent across blocks?
+2. LENS present with mm (live-action) OR stylistic anchor with
+   film+year (animated)?
+3. LIGHTING with a direction?
+4. ACTION names beat counts, not adjectives?
+5. DIALOGUE / AMBIENT SOUND present → the run requires `audio:
+   native` adapter OR ffmpeg-mux fallback declared.
+6. NEGATIVE ≥ 4 entries, load-bearing top?
+7. SUBJECT verbatim from `character.json` when a lock exists?
+
+Any "no" → revise that block.
+
+### Step 3: Validate
+
+1. Pipe output through `scripts/ai-video/lib/parse-blueprint.sh` —
+   exits 0 and emits valid adapter-contract JSON.
+2. No provider tokens (no aspect / model / duration flags).
+
+## Output format
+
+1. **`scenes/<id>/prompt.txt`** — 12 labeled blocks, ready for
+   `parse-blueprint.sh`.
+2. **`scenes/<id>/blueprint.json`** — parser output, adapter-stdin
+   ready.
+3. **`scenes/<id>/review.md`** — one-paragraph rationale per
+   non-obvious choice.
+
+## Gotcha
+
+- The model wants to skip optional DIALOGUE / AMBIENT SOUND blocks
+  silently — if they could plausibly belong, emit them; the parser
+  treats missing blocks as `null`, not as an error.
+- Live-action without LENS mm fails the parser's strict mode.
+- Animated without a film+year anchor in STYLE drifts on every run.
+- ACTION written as "the character does X dramatically" fails —
+  adapters need verbs with beat counts.
+- DIALOGUE forces `audio: native` requirement — flag this to the
+  orchestrator so it picks a capable adapter (Veo / Sora).
+
+## Do NOT
+
+- Do NOT emit provider tokens — that is `motion-choreographer`.
+- Do NOT skip the blueprint parser validation step.
+- Do NOT paraphrase identity tokens when a lock exists.
+- Do NOT mix live-action LENS prescriptions with animated STYLE
+  anchors in the same scene — pick one mode.
+
+## Policies
+
+The 12-block Cinematic Scene Blueprint is the policy choke point — every downstream skill (`motion-choreographer`, `video-director`) inherits whatever the blueprint encodes. Before emitting:
+
+- [`agents/policies/media/likeness.md`](../../../agents/policies/media/likeness.md) — when the SUBJECT block names or visually identifies a real person.
+- [`agents/policies/media/public-figures.md`](../../../agents/policies/media/public-figures.md) — when the SUBJECT block is a recognised public figure.
+- [`agents/policies/media/brand-impersonation.md`](../../../agents/policies/media/brand-impersonation.md) — when STYLE / ENVIRONMENT references a recognised brand's visual identity.
+- [`agents/policies/media/style.md`](../../../agents/policies/media/style.md) — when STYLE anchors to a named living artist or studio as the primary signature.
+- [`agents/policies/media/disclosure.md`](../../../agents/policies/media/disclosure.md) — every distributed blueprint output carries the AI-generation disclosure downstream.
+
+Refuse-and-surface at the blueprint layer; do not push policy questions down to the adapter.
+

package/.agent-src/skills/scene-expander/scene-blueprint.schema.yaml

@@ -0,0 +1,108 @@
+# Scene Blueprint Schema (v1)
+#
+# Maps the 12 labeled blocks emitted by `scene-expander` to the
+# adapter-contract JSON consumed by every adapter under
+# `scripts/ai-video/adapters/`. Validation lives in
+# `scripts/ai-video/lib/parse-blueprint.sh`.
+#
+# Source format: plain-text, one labeled block per line OR per
+# heading. Labels are case-insensitive; whitespace around `:` is
+# tolerated. Block order is the canonical order below — out-of-order
+# blocks are accepted but logged as a warning.
+
+version: 1
+
+blocks:
+  STYLE:
+    required: true
+    target: prompt.style
+    description: "Film stock + decade (live-action) or film title + year (animated)."
+
+  SUBJECT:
+    required: true
+    target: prompt.subject
+    description: "Character read. Verbatim from character.json when locked."
+
+  ENVIRONMENT:
+    required: true
+    target: prompt.environment
+    description: "Location, time-of-day, weather, era; world reaction."
+
+  ACTION:
+    required: true
+    target: prompt.action
+    description: "Anticipation / action / reaction with beat counts."
+
+  CAMERA:
+    required: true
+    target: prompt.camera
+    description: "Position, height, distance, move."
+
+  LENS:
+    required: true
+    target: prompt.lens
+    description: "Focal length in mm + aperture intent (live-action). Animated runs may emit 'n/a' but the block must be present."
+
+  LIGHTING:
+    required: true
+    target: prompt.lighting
+    description: "Key / fill / back / practical with direction."
+
+  MOOD:
+    required: true
+    target: prompt.mood
+    description: "Single emotional read."
+
+  DIALOGUE:
+    required: false
+    target: audio.dialogue
+    description: "Optional. Marks audio.native requirement when present."
+    null_when_absent: true
+
+  AMBIENT SOUND:
+    required: false
+    target: audio.ambient
+    description: "Optional ambient layer list."
+    null_when_absent: true
+
+  DURATION:
+    required: true
+    target: duration
+    type: number
+    description: "Seconds. Integer or one decimal."
+
+  NEGATIVE:
+    required: true
+    target: negative
+    description: "Clichés to reject, load-bearing top-first."
+
+# Adapter-contract JSON shape produced by parse-blueprint.sh
+output_shape: |
+  {
+    "prompt": {
+      "style": "...",
+      "subject": "...",
+      "environment": "...",
+      "action": "...",
+      "camera": "...",
+      "lens": "...",
+      "lighting": "...",
+      "mood": "..."
+    },
+    "audio": {
+      "dialogue": [...] | null,
+      "ambient": [...] | null,
+      "enable_native_audio": true | false
+    },
+    "duration": 5.0,
+    "negative": ["...", "..."],
+    "requires": {
+      "audio_native": true | false
+    }
+  }
+
+# `enable_native_audio` derives from: DIALOGUE present OR AMBIENT SOUND present.
+# Orchestrator uses `requires.audio_native` to pick an adapter with
+# `audio: native` capability (Phase 4 Step 1). When no native adapter
+# is available the orchestrator routes audio.* to ffmpeg mux at
+# stitch time (Phase 4 Step 7) and clears `enable_native_audio`.

package/.agent-src/skills/subagent-orchestration/SKILL.md

@@ -56,7 +56,7 @@ model pairing. Defaults come from
 Descriptive, not enforced. Documents the **expected agent-to-agent
 communication topology** so consumers can predict latency, failure
 modes, and where consensus is required. Cited from
-[`external-findings.md § 2`](../../../agents/audit-2026-05-14-north-star/external-findings.md)
+[`external-findings.md § 2`](../../../agents/council-sessions/audit-2026-05-14-north-star/external-findings.md) <!-- council-ref-allowed: ADR decision trace for topology anti-drift defaults -->
 row 7 (Ruflo's `hierarchical, 6–8 agents, raft consensus` anti-drift
 default).
 
@@ -72,8 +72,8 @@ default).
 
 **Anti-drift default** (Ruflo convention, descriptive only):
 `hierarchical, 6–8 agents, raft consensus`. Consumers free to
-override per orchestration — table is **starting point**, not a
-constraint. Topology is metadata for capacity planning, not
+override per orchestration — the table is the **starting point**,
+not a constraint. Topology is metadata for capacity planning, not
 runtime-enforced.
 
 **Glossary:**
@@ -81,7 +81,7 @@ runtime-enforced.
 - `mesh` — agents see each other's outputs (e.g. competing diffs).
 - `hierarchical-mesh` — peer debate followed by hub reconciliation.
 - `ring` — output of step N feeds input of step N+1 in order.
-- `star` — N agents fan out from single hub; no peer comms.
+- `star` — N agents fan out from a single hub; no peer comms.
 - `adaptive` — topology shifts per step; outer chain remains hub.
 
 ### 1. do-and-judge
@@ -193,17 +193,19 @@ step is under ~30 minutes. The branch-creation, context-switch, and
 worktree-cleanup cost dominates. Stick with mode 1 (do-and-judge)
 or mode 3 (do-in-steps) for those.
 
-**Competitive variant — per-candidate isolation.** Mode 5
-(`do-competitively`) + worktrees: each candidate runs in its own
-worktree (no cross-candidate state leak). Selection rules:
-
-- **No auto-merge.** Orchestrator never merges candidate branches.
-  Hard Floor per [`non-destructive-by-default`](../../rules/non-destructive-by-default.md) —
-  applies even under standing autonomy. ADR-005 records reasoning.
-- **Ranked presentation.** Judge ranks 1..N with one-line
-  justifications; user picks winner.
-- **Loser worktrees stay.** Orchestrator does not auto-delete losing
-  worktrees — user keeps option to harvest a partial idea before cleanup.
+**Competitive variant — per-candidate isolation.** When mode 5
+(`do-competitively`) is combined with worktrees, each candidate
+implementer runs in its own worktree (so candidates cannot read each
+other's open files or branch state). Selection rules:
+
+- **No auto-merge.** The orchestrator never merges a candidate
+  branch. Hard Floor per [`non-destructive-by-default`](../../rules/non-destructive-by-default.md) —
+  applies even under standing autonomy. ADR-005 records the reasoning.
+- **Ranked presentation.** Judge ranks candidates (1..N) with a
+  one-line justification per rank; user picks the winner.
+- **Loser worktrees stay.** The orchestrator does not delete losing
+  worktrees automatically — the user keeps the option to harvest a
+  partial idea before cleanup.
 
 ## Status taxonomy — every subagent return uses one envelope
 

package/.agent-src/skills/video-director/SKILL.md

@@ -0,0 +1,126 @@
+---
+name: video-director
+description: "Use when turning a scene idea into the 11-block cinematic prompt for live-action AI video — lens, lighting, blocking, motion, negatives. Triggers 'cinematic prompt', 'film-grade scene'."
+personas:
+  - hollywood-director
+source: package
+domain: product
+---
+
+# video-director
+
+> Turn a scene idea into the **11-block cinematic prompt** the
+> `hollywood-director` persona ships. Output is provider-agnostic
+> prose; provider-specific tuning is handed off to
+> [`motion-choreographer`](../motion-choreographer/SKILL.md).
+
+## When to use
+
+- A scene idea, beat, or script line needs to become a cinematic
+  prompt ready to feed an image+video pipeline.
+- A draft prompt reads as "AI video" — flat, centered, generic
+  golden-hour — and needs directorial choices on the page.
+- Live-action / photoreal scenes. For animation acting beats, route
+  to [`pixar-storyteller`](../pixar-storyteller/SKILL.md).
+
+Do NOT use when:
+
+- The deliverable is a still graphic or poster → `canvas-design`.
+- The work is provider-specific token tuning →
+  `motion-choreographer` after this skill has produced the blocks.
+- A character identity must be re-used across scenes → run
+  [`character-consistency`](../character-consistency/SKILL.md) first
+  to lock identity tokens, then call this skill.
+
+## Procedure
+
+### Step 0: Inspect
+
+1. Confirm the input is a live-action / photoreal beat (not animation).
+2. If a `character.json` exists under `agents/ai-video/<project>/characters/`,
+   read the identity tokens — they are reused verbatim.
+3. Read the scene's intent in one sentence — what is the camera
+   witnessing, and why now?
+
+### Step 1: Draft the 11 blocks
+
+Emit each block on its own labeled line. Blocks are mandatory and
+in this order:
+
+1. **SCENE** — location, time-of-day, weather, era.
+2. **CHARACTER** — verbatim identity tokens from `character.json`
+   when present; otherwise silhouette + wardrobe + signature prop.
+3. **ACTION** — verbs and beats. Anticipation → action → reaction
+   named separately. No "doing things" prose.
+4. **CAMERA** — position, height, distance, move (lock-off, dolly,
+   handheld, push, pull). Off-axis when on-axis is the AI default.
+5. **LENS** — focal length in mm (24 / 35 / 50 / 85 / 200) and
+   aperture intent (deep / shallow). "Cinematic" alone fails.
+6. **LIGHTING** — key, fill, back, practical sources named. "Golden
+   hour" requires an angle (low-east 15°, etc.).
+7. **ENVIRONMENT MOTION** — what the world does (wind, water,
+   crowd, traffic) and on which beat.
+8. **SECONDARY MOTION** — hair, cloth, dust, breath. Names the
+   reactive layer that sells the primary action.
+9. **MOOD** — one emotional read; no compound moods.
+10. **DURATION** — seconds. Integer or one decimal.
+11. **NEGATIVE CONSTRAINTS** — clichés to reject, in load-bearing
+    order (top survives truncation). Always names: centered framing,
+    symmetric composition, generic "cinematic", soap-opera contrast.
+
+### Step 2: Self-review
+
+1. Lens length present? "Cinematic" without mm → fail.
+2. Lighting direction present? "Golden hour" without angle → fail.
+3. ACTION names beats, not adjectives?
+4. NEGATIVE block has at least 4 entries, load-bearing on top?
+5. CHARACTER block reuses identity tokens verbatim when a lock exists?
+
+Any "no" → revise that block before handing off.
+
+### Step 3: Validate
+
+1. Output is plain text, one labeled block per line, ready for
+   `scripts/ai-video/lib/parse-blueprint.sh` (Phase 3 Step 5).
+2. No provider tokens (no `--aspect`, no `--model`). That is
+   `motion-choreographer`'s job.
+
+## Output format
+
+1. **`scenes/<id>/prompt.txt`** — 11 labeled blocks, one per line,
+   ready for the blueprint parser.
+2. **`scenes/<id>/review.md`** — one-paragraph rationale per
+   non-obvious directorial choice (lens, light angle, camera move).
+
+## Gotcha
+
+- The model defaults to centered, on-axis, symmetric — name an
+  off-axis or rule-of-thirds camera or it will silently center.
+- "Golden hour" alone reads as a sunset GIF; require a sun angle.
+- ACTION written as a paragraph of adjectives ("dynamically", "powerfully")
+  fails — adapters need verbs with beat counts.
+- When `character.json` exists, paraphrasing identity tokens breaks
+  Character Lock — copy them verbatim.
+- Negative constraints in the truncated tail get dropped — load-
+  bearing ones go first.
+
+## Do NOT
+
+- Do NOT emit provider-specific tokens (aspect ratio, model id,
+  duration flags) — that is `motion-choreographer`'s scope.
+- Do NOT collapse anticipation / action / reaction into one verb.
+- Do NOT use "cinematic" without lens + lighting + camera move.
+- Do NOT invent character details when a `character.json` exists.
+
+## Policies
+
+11-block cinematic prompt is live-action shape — real-person + brand-impersonation risks highest in cluster. Before emitting:
+
+- [`agents/policies/media/likeness.md`](../../../agents/policies/media/likeness.md) — prompt names / visually identifies real person on camera.
+- [`agents/policies/media/public-figures.md`](../../../agents/policies/media/public-figures.md) — subject is recognised public figure.
+- [`agents/policies/media/brand-impersonation.md`](../../../agents/policies/media/brand-impersonation.md) — prompt copies journalism / broadcaster / regulated-industry visual identity.
+- [`agents/policies/media/style.md`](../../../agents/policies/media/style.md) — LIGHT / LENS anchored to named living cinematographer's signature.
+- [`agents/policies/media/disclosure.md`](../../../agents/policies/media/disclosure.md) — every distributed live-action AI clip carries non-removable AI-generation disclosure.
+
+Refuse-and-surface at directorial layer; live-action realism amplifies every downstream policy gap.
+

package/.agent-src/templates/agent-settings.md

@@ -217,6 +217,23 @@ roadmap:
   # mandatory before any "roadmap complete" claim, regardless of cadence.
   quality_cadence: end_of_roadmap
 
+# --- Quality / CI execution ---
+quality:
+  # Run local quality / CI tasks and tests autonomously (true, false)
+  # true  = agent runs the quality pipeline whenever work is ready
+  #         for verification, without asking (default)
+  # false = agent asks before running quality tools / tests locally
+  # Carve-out: NEW CI gates / smoke tests / test files MUST run
+  # locally regardless of this flag — without execution the gate is
+  # unverified evidence. Iron Law `verify-before-complete` still applies.
+  local_auto_run: true
+
+  # Wait for remote CI to finish on the PR / pipeline (true, false)
+  # true  = poll GitHub check-runs / pipeline after push and report
+  #         green / red before handing back
+  # false = push and hand back immediately (default)
+  wait_for_remote_ci: false
+
 # --- Subagent orchestration ---
 subagents:
   # Model for implementer subagents (empty = same tier as the session model)
@@ -447,6 +464,8 @@ the canonical narrative lives in
 | `hooks.chat_history.script` | path | `scripts/chat_history.py` | Override path to the chat-history CLI. Set only when the script lives outside the standard location. |
 | `pipelines.skill_improvement` | `true`, `false` | `true` | When `true`: propose learning capture after meaningful tasks. When `false`: silent. Included in every profile except `custom`. |
 | `roadmap.quality_cadence` | `end_of_roadmap`, `per_phase`, `per_step` | `end_of_roadmap` | When `/roadmap:process-step|phase|full` runs the project's quality pipeline. Default skips per-step / per-phase runs and gates only the final archival. `per_phase` runs once after every phase; `per_step` is the legacy verbose mode. Step checkboxes and the dashboard are always updated regardless. `verify-before-complete` still requires fresh output before any "roadmap complete" claim. |
+| `quality.local_auto_run` | `true`, `false` | `true` | When `true`: agent runs the project's quality pipeline (`task ci`, `make test`, `npm run check`, PHPStan, ECS, Rector, test suites) autonomously when work is ready for verification. When `false`: agent asks before running locally. **Carve-out**: NEW CI gates / smoke tests / test files MUST run locally regardless of this flag — without execution the new gate is unverified evidence. Iron Law `verify-before-complete` still applies; suppressed runs require the agent to surface the gap before claiming completion. |
+| `quality.wait_for_remote_ci` | `true`, `false` | `false` | When `true`: after `git push`, the agent polls GitHub check-runs / pipeline status on the PR and reports green / red before handing back. When `false`: agent pushes and hands back immediately; the user inspects CI themselves (default — saves agent runtime and tokens). |
 | `subagents.implementer_model` | model alias or empty | _(empty)_ | Model for implementer subagents. Empty = same tier as session model. See [subagent-configuration](../contexts/subagent-configuration.md). |
 | `subagents.judge_model` | model alias or empty | _(empty)_ | Model for judge subagents. Empty = one tier above implementer (opus if sonnet, sonnet if haiku). |
 | `subagents.max_parallel` | integer | `3` | Maximum parallel subagent invocations. `1` serializes. |

package/.agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.py (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "2.21.0"
+agent_config_version: "2.24.0"
 
 # --- Project identity ---
 project:

package/.agent-src/templates/roadmaps.md

@@ -84,6 +84,22 @@ php artisan test                     # Tests (or: vendor/bin/phpunit)
 
 Check `AGENTS.md` or `Makefile` / `Taskfile.yml` for the exact commands.
 
+### CI-step gate (when `quality.local_auto_run: false`)
+
+Roadmaps **must not** schedule full-pipeline literals (`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`) as checkbox
+steps when `quality.local_auto_run` is `false` in
+`.agent-settings.yml` — `task lint-roadmap-ci-steps` blocks them.
+Reword as narrow verifications (`vendor/bin/phpstan analyse
+app/Modules/X`, `php artisan test --filter=…`) or mark with
+`<!-- carve-out: new-gate-verification -->` when the step verifies a
+**new** gate this roadmap introduces. At execution,
+`/roadmap:process-*` flips matching steps to `[-]` with reason and
+skips them. Full contract:
+[`roadmap-ci-steps-policy`](../rules/roadmap-ci-steps-policy.md).
+
 ---
 
 ## Template