@event4u/agent-config 2.21.0 → 2.24.0

package/.agent-src/skills/refine-prompt/SKILL.md

@@ -54,6 +54,50 @@ calling command (`/work`) owns prompt capture; this skill only refines.
 If `raw` is missing, empty, or whitespace-only the resolver already
 raised `PromptResolverError`. The skill never receives that input.
 
+## Modes and bypass
+
+The skill honours `prompt_optimization.inbound` (or
+`prompt_optimization.default` when no inbound override is set) from
+`.agent-project-settings.yml` / `.agent-settings.yml`. Three modes:
+
+| Mode | Behaviour |
+|---|---|
+| `off` | The skill is a no-op. The dispatcher writes `confidence={"band":"high","score":1.0}` directly and the engine proceeds with the literal prompt. No assumption inference, no clarifying questions. |
+| `mini` | Stack-aware light shaping. Steps 1-2 run; step 3 only emits `assumes:` lines for *implicit stack constraints* (framework, package manager) detected from config files. Steps 4-5 produce 3 AC bullets max. Low-band halts ask at most one question; medium-band halts are auto-confirmed silently. |
+| `max` *(default)* | Full procedure — every step 1–6 runs. Medium-band halts surface the assumption list verbatim; low-band halts ask one clarifying question. This is the existing behaviour. |
+
+**Bypass prefix.** If the raw prompt starts with the configured
+`prompt_optimization.bypass_prefix` (default `/raw`), the skill
+becomes a no-op regardless of mode. The dispatcher strips the
+prefix, passes the remainder through verbatim, and records
+`bypass:true` in the envelope so downstream surfaces (delivery
+report, `--no-prose-synthesis`) can attribute the skip.
+
+```
+/raw migrate auth.service.ts to use jose, keep the API shape
+```
+
+`/raw` is reserved at the prompt boundary only — it has no meaning
+mid-prompt and is not stripped when it appears inside the body.
+
+### Stack-config read (mini / max only)
+
+When the mode is `mini` or `max`, step 3 may read these config files
+(read-only, scope-locked) to enrich the `assumes:` block:
+
+- `package.json` — JS / TS framework detection (Next.js App vs Pages,
+  Remix, SvelteKit, Astro, Expo, …)
+- `composer.json` — PHP framework detection (Laravel, Symfony,
+  framework-less)
+- `pyproject.toml` / `requirements.txt` — Python framework detection
+- `CLAUDE.md` / `AGENTS.md` — project-declared stack hints
+- `.cursorrules` — project-declared stack hints
+- `tsconfig.json` — TS path-alias / module-resolution hints
+
+The skill MUST NOT read source files, `.env*`, secrets, or user
+data. Detection lands as a single `assumes: stack=<framework>@<version>`
+line; the medium-band halt is the user's chance to flip it.
+
 ## Procedure
 
 ### 1. Read and analyze the prompt
@@ -220,11 +264,24 @@ For `low`, the question replaces the AC list:
   `data.reconstructed_ac` and `data.assumptions`.
 - Do NOT re-derive band thresholds in prose. They live in
   `confidence.py` and only there.
+- Do NOT read source files, `.env*`, secrets, or arbitrary user
+  files when stack-detecting in mini / max mode. The allowlist
+  above (`package.json`, `composer.json`, `pyproject.toml`,
+  `requirements.txt`, `CLAUDE.md`, `AGENTS.md`, `.cursorrules`,
+  `tsconfig.json`) is exhaustive.
+- Do NOT strip the `bypass_prefix` mid-prompt. The prefix is only
+  recognised at the prompt boundary; matches inside the body stay
+  literal.
+- Do NOT silently rewrite the prompt in `max` mode without
+  surfacing the assumption list on a medium-band halt. The diff
+  is the contract.
 
 ## See also
 
 - [`refine-ticket`](../refine-ticket/SKILL.md) — sibling for ticket-shaped input
+- [`prompt-optimizer`](../prompt-optimizer/SKILL.md) — engine-outbound sibling; same `prompt_optimization` setting controls its mode
 - [`work_engine.resolvers.prompt`](../../templates/scripts/work_engine/resolvers/prompt.py) — envelope builder
 - [`work_engine.scoring.confidence`](../../templates/scripts/work_engine/scoring/confidence.py) — rubric + band thresholds
 - [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) — one-question-per-turn Iron Law
 - [`artifact-drafting-protocol`](../../rules/artifact-drafting-protocol.md) — this skill was drafted under it
+- AI Council session: `agents/council-responses/prompt-master-mini.json` (2026-05-17) — analysis behind the mini/max split and `/raw` bypass <!-- council-ref-allowed: ADR decision trace -->

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

@@ -0,0 +1,122 @@
+---
+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
+  - pixar-storyboard-artist
+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 and `pixar-storyboard-artist`
+> for animated beats. 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 → load
+   `pixar-storyboard-artist`. 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.

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/tailwind-engineer/SKILL.md

@@ -117,6 +117,20 @@ Risks:          <arbitrary values, !important, dark-mode gaps>
   break the design system; they accumulate silently.
 - `@apply` inside component CSS interacts with PurgeCSS — keep it
   in files Tailwind scans, not in vendor CSS.
+- **Anti-AI-slop: gradients.** Unless audit-pinned or brief-explicit,
+  avoid the default purple-to-blue / cyan-to-pink gradients on white —
+  they read as auto-generated. Reach for a single accent from the
+  token map, or a duotone built from configured tokens.
+- **Anti-AI-slop: typography.** Unless audit-pinned, avoid surfacing
+  the system stack (`font-sans` fallback to Arial / Helvetica / Inter
+  via system defaults) as the *visible* body face. If `tailwind.config`
+  pins a font family, use it; if not, treat the missing token as a
+  gap to flag, not a license to ship the OS default.
+- **Anti-AI-slop: layout.** Unless audit-pinned, the centered hero +
+  3-column features + CTA stack is the AI-template tell. Break the
+  grid intentionally (asymmetric column split, overlap, diagonal
+  flow) when the brief allows; cite the design brief's `aesthetic:`
+  line if `fe-design`'s aesthetic-direction section produced one.
 
 ## Do NOT
 

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

@@ -0,0 +1,113 @@
+---
+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.

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: "2.20.1"
+agent_config_version: "2.23.0"
 
 # --- Project identity ---
 project:
@@ -152,6 +152,58 @@ quality:
     # Known: eslint, prettier, tsc, biome.
     tools: [eslint, prettier, tsc]
 
+# --- Prompt optimization (engine-inbound + engine-outbound) ---
+#
+# Controls how aggressively the agent reshapes a free-form prompt
+# *before* the engine plans (`/work "<prompt>"`) and how the
+# outbound `/optimize-prompt` skill polishes a copy-and-paste
+# prompt for an external AI.
+#
+# Single-knob model — `default:` applies to both inbound and
+# outbound surfaces unless an override key is set:
+#
+#   off  — engine runs the user's literal prompt. No reconstruction,
+#          no AC inference, no template selection. Closest to "raw"
+#          behaviour; useful for power users who already write
+#          structured prompts.
+#   mini — light shaping. Inbound: `refine-prompt` runs in
+#          stack-aware mode (reads `package.json` / `CLAUDE.md` /
+#          `.cursorrules` only to infer the framework), asks at
+#          most 5 targeted clarifying questions, emits a structured
+#          6-block prompt. Outbound: BASIC mode of `prompt-optimizer`
+#          (4-D pass with safe defaults, no clarifying questions).
+#   max  — full restructure. Inbound: `refine-prompt` runs the
+#          5-dimension confidence rubric + assumption inference;
+#          medium-band halts surface the assumption list, low-band
+#          asks one clarifying question. Outbound: DETAIL mode of
+#          `prompt-optimizer` with template selection (RTF, CO-STAR,
+#          RISEN, CRISPE, …) per `docs/guidelines/prompt-templates.md`.
+#
+# Default `max` reshapes every prompt before the engine plans —
+# the AI Council (anthropic/openai, 2026-05-17) warned this risks
+# latency, token cost, and loss of author intent on the inbound
+# side. If that bites you, uncomment `inbound: mini` below. The
+# outbound side (explicit `/optimize-prompt`) is opt-in and stays
+# at `max` regardless.
+#
+# Bypass: any prompt starting with `bypass_prefix` skips both
+# inbound and outbound shaping verbatim. `/`-prefixed slash
+# commands (`/work`, `/commit`, …) and `#`-prefixed memory entries
+# auto-bypass.
+prompt_optimization:
+  default: max
+
+  # Optional per-surface overrides. Leave commented to inherit
+  # `default:`. Council-recommended split is `inbound: mini,
+  # outbound: max` — uncomment if you want fewer interceptions
+  # on `/work` but full polish on `/optimize-prompt`.
+  # inbound: mini
+  # outbound: max
+
+  # Prefix that skips all shaping. Must start with `/` to align
+  # with this project's slash-command convention. Default `/raw`.
+  bypass_prefix: "/raw"
+
 # --- Locked keys (override this file only; never locks .agent-settings.yml) ---
 #
 # List keys from this file whose values cannot be overridden by a

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Shared agent configuration \u2014 skills for AI coding tools (Claude Code, Augment, Cursor, Cline, Windsurf, Gemini CLI).",
-    "version": "2.21.0",
+    "version": "2.24.0",
     "keywords": [
       "agent-config",
       "skills",
@@ -85,6 +85,7 @@
         "./.claude/skills/chat-history-import",
         "./.claude/skills/chat-history-learn",
         "./.claude/skills/chat-history-show",
+        "./.claude/skills/character-consistency",
         "./.claude/skills/check-current-md",
         "./.claude/skills/check-refs",
         "./.claude/skills/churn-prevention",
@@ -236,6 +237,7 @@
         "./.claude/skills/module-create",
         "./.claude/skills/module-explore",
         "./.claude/skills/module-management",
+        "./.claude/skills/motion-choreographer",
         "./.claude/skills/multi-tenancy",
         "./.claude/skills/nextjs-patterns",
         "./.claude/skills/okr-tree-modeling",
@@ -267,6 +269,7 @@
         "./.claude/skills/php-debugging",
         "./.claude/skills/php-service",
         "./.claude/skills/pipeline-strategy",
+        "./.claude/skills/pixar-storyteller",
         "./.claude/skills/playwright-architect",
         "./.claude/skills/playwright-testing",
         "./.claude/skills/po-discovery",
@@ -324,6 +327,7 @@
         "./.claude/skills/rule-writing",
         "./.claude/skills/runway-cognition",
         "./.claude/skills/scenario-modeling",
+        "./.claude/skills/scene-expander",
         "./.claude/skills/script-writing",
         "./.claude/skills/secrets-management",
         "./.claude/skills/security",
@@ -367,6 +371,12 @@
         "./.claude/skills/using-git-worktrees",
         "./.claude/skills/validate-feature-fit",
         "./.claude/skills/verify-completion-evidence",
+        "./.claude/skills/video",
+        "./.claude/skills/video-director",
+        "./.claude/skills/video-from-script",
+        "./.claude/skills/video-scene",
+        "./.claude/skills/video-stitch",
+        "./.claude/skills/video-storyboard",
         "./.claude/skills/vision-articulation",
         "./.claude/skills/voc-extract",
         "./.claude/skills/voice-and-tone-design",