@event4u/agent-config 2.24.0 → 2.26.0

package/.agent-src/commands/package-test.md

@@ -1,7 +1,7 @@
 ---
 name: package-test
 tier: 2
-skills: [composer, npm]
+skills: [composer, npm, python-packages, go-modules, cargo-packages]
 description: /package-test
 disable-model-invocation: true
 suggestion:
@@ -17,15 +17,28 @@ Test a local package in the current project by linking it via Composer or npm.
 
 ### 1. Detect or ask for package manager
 
-Check the project root for `composer.json` and `package.json`.
+Check the project root for a package manifest. Supported (try in this order, take the first match — the project can have several):
 
-- **Both exist** → ask:
+| Manifest                                                          | Ecosystem        | Link mechanism                                           |
+|-------------------------------------------------------------------|------------------|----------------------------------------------------------|
+| `composer.json`                                                   | PHP / Composer   | `repositories[].type: path` + `composer require @dev`    |
+| `package.json`                                                    | JS / TS / Node   | `npm link` / `pnpm link` / `yarn link` / `file:../path`  |
+| `pyproject.toml`, `setup.py`, or `setup.cfg`                      | Python           | `pip install -e <path>` / `uv pip install -e <path>` / `poetry add --editable <path>` |
+| `go.mod`                                                          | Go               | `go mod edit -replace example.com/pkg=<path>`            |
+| `Cargo.toml`                                                      | Rust             | `cargo add --path <path>` or `[patch.crates-io]` block   |
+| `Gemfile`                                                         | Ruby             | `bundle config local.<gem> <path>`                       |
+
+- **Multiple manifests exist** → ask:
 
 ```
 Which package manager?
 
 1. Composer (PHP)
-2. npm (JavaScript/TypeScript)
+2. npm / pnpm / yarn (JavaScript / TypeScript)
+3. Python (pip / poetry / uv)
+4. Go modules
+5. Cargo (Rust)
+6. Bundler (Ruby)
 ```
 
 - **Only one exists** → use that one automatically, confirm:
@@ -37,7 +50,7 @@ Detected: {manager}. Proceeding.
 - **Neither exists** → abort:
 
 ```
-❌  No composer.json or package.json found in project root. Cannot link a local package.
+❌  No supported package manifest (composer.json / package.json / pyproject.toml / setup.py / go.mod / Cargo.toml / Gemfile) found in project root. Cannot link a local package.
 ```
 
 ### 2. Ask for the local package path
@@ -51,15 +64,19 @@ Example: ../my-package or /Users/me/projects/my-package
 
 Validate:
 - Path exists and is a directory
-- For Composer: directory contains `composer.json`
-- For npm: directory contains `package.json`
+- The directory contains a manifest matching the ecosystem chosen in the detection step (`composer.json`, `package.json`, `pyproject.toml` / `setup.py`, `go.mod`, `Cargo.toml`, or `Gemfile`)
+- If the directory has multiple manifests, ask the user which one to link (rare but possible — e.g. a Composer package that also ships a JS bundle)
 
 If invalid, show error and ask again.
 
 ### 3. Read the package name
 
-- **Composer:** Read `name` from the package's `composer.json`
-- **npm:** Read `name` from the package's `package.json`
+- **Composer:** Read `name` from the package's `composer.json` (e.g. `vendor/package`)
+- **npm / pnpm / yarn:** Read `name` from the package's `package.json` (e.g. `@scope/package`)
+- **Python:** Read `[project].name` from `pyproject.toml`, or `setup(name=...)` from `setup.py`
+- **Go:** Read `module` from `go.mod` (e.g. `example.com/vendor/package`)
+- **Rust:** Read `[package].name` from `Cargo.toml`
+- **Ruby:** Read the gem name from the `*.gemspec` file in the package directory
 
 Confirm:
 
@@ -118,10 +135,69 @@ Or for workspaces, add to `package.json`:
 
 Then: `npm install`
 
+#### Python
+
+Editable install (preferred):
+
+```bash
+pip install -e {package-path}
+# or, if the project uses uv:
+uv pip install -e {package-path}
+# or, if the project uses poetry:
+cd {project-root} && poetry add --editable {package-path}
+```
+
+Re-sync after upstream changes:
+
+```bash
+pip install -e {package-path} --force-reinstall --no-deps
+```
+
+#### Go
+
+Edit `go.mod` in the **project** root to add a `replace` directive:
+
+```
+replace example.com/vendor/package => ../my-package
+```
+
+Then run `go mod tidy` so the lockfile picks up the local path. Remove the `replace` line before publishing.
+
+#### Rust / Cargo
+
+Add as a path dependency in the **project's** `Cargo.toml`:
+
+```toml
+[dependencies]
+vendor_package = { path = "../my-package" }
+```
+
+Or, to override a published crate without rewriting the dependency line, use `[patch.crates-io]`:
+
+```toml
+[patch.crates-io]
+vendor_package = { path = "../my-package" }
+```
+
+Run `cargo build` to re-resolve.
+
+#### Ruby / Bundler
+
+```bash
+bundle config local.{gem-name} {package-path}
+bundle install
+```
+
+Remove with `bundle config --delete local.{gem-name}`.
+
 ### 5. Verify
 
 - **Composer:** Check that `vendor/{package-name}` is a symlink → the local path
-- **npm:** Check that `node_modules/{package-name}` is a symlink → the local path
+- **npm / pnpm / yarn:** Check that `node_modules/{package-name}` is a symlink → the local path
+- **Python:** `pip show {package-name}` → `Location` should point inside `{package-path}` (editable installs show the source dir, not site-packages)
+- **Go:** `go list -m {module-path}` → resolved path should match the `replace` target
+- **Rust:** `cargo metadata --format-version 1 | jq '.packages[] | select(.name=="{package-name}") | .manifest_path'` → should point inside `{package-path}`
+- **Ruby:** `bundle config get local.{gem-name}` → should return the linked path
 
 Report result:
 

package/.agent-src/commands/quality-fix.md

@@ -6,8 +6,8 @@ description: Run quality pipeline (PHP and/or JS/TS) and fix all errors — auto
 disable-model-invocation: true
 suggestion:
   eligible: true
-  trigger_description: "fix the quality errors, run PHPStan and fix issues, fix code style"
-  trigger_context: "PHPStan/Rector/ECS output in recent tool results"
+  trigger_description: "fix the quality errors — run the project's type-checker / linter / formatter and resolve every issue (PHPStan / tsc / mypy / golangci-lint / clippy / …)"
+  trigger_context: "type-checker / linter / formatter output in recent tool results (PHPStan, Rector, ECS, tsc, eslint, prettier, ruff, mypy, golangci-lint, clippy)"
 ---
 
 # quality-fix
@@ -33,34 +33,56 @@ git diff --name-only origin/{default}..HEAD
 ### Prerequisites
 
 - All commands run **inside the PHP container** (e.g. `docker compose exec -T <service> ...`).
-- Detect the project type:
-  - Project ships a `quality:*` wrapper (Artisan or Composer script) → prefer `php artisan quality:phpstan` / `php artisan quality:rector --fix`
-  - `phpstan/phpstan` installed → `vendor/bin/phpstan analyse`
-  - `rector/rector` installed → `vendor/bin/rector process`
-  - `symplify/easy-coding-standard` installed → `vendor/bin/ecs check --fix`
-
-### Step 1: PHPStan — fix all errors
-
-1. Run PHPStan and capture the full output.
+- Detect the project's quality toolchain **before** doing anything else. Pick the first match:
+  1. Project ships a wrapper script — prefer the wrapper over invoking tools directly:
+     - PHP: `php artisan quality:*` (Laravel), `composer run quality`, `composer run lint`
+     - JS / TS: `npm run lint`, `npm run typecheck`, `pnpm lint`, `pnpm typecheck`, `yarn lint`, `yarn typecheck`
+     - Python: `make lint`, `nox -s lint`, `tox -e lint`
+     - Polyglot: `Taskfile.yml`, `Makefile`, or `justfile` with a `quality` / `lint` / `check` target
+  2. No wrapper — invoke tools directly based on which are installed:
+     - PHP: `vendor/bin/phpstan analyse`, `vendor/bin/rector process`, `vendor/bin/ecs check --fix`
+     - JS / TS: `npx tsc --noEmit`, `npx eslint . --fix`, `npx prettier . --write`, `npx biome check --apply`
+     - Python: `ruff check . --fix`, `ruff format .`, `mypy .`, `pyright`
+     - Go: `golangci-lint run --fix`, `go vet ./...`, `gofmt -w .`
+     - Rust: `cargo clippy --fix --allow-dirty`, `cargo fmt`
+  3. Nothing detected → ask the user which command runs the project's quality pipeline. Do not invent one.
+
+### Step 1: Type-checker — fix all errors
+
+Run the project's type-checker (chosen in the detection step):
+- PHP → PHPStan
+- JS / TS → `tsc --noEmit`
+- Python → mypy / pyright
+- Go → `go vet` + `go build`
+- Rust → `cargo check`
+
+1. Run the type-checker and capture the full output.
 2. For each error, **fix it in code**. Resolve the root cause.
-3. **Do NOT add errors to the baseline or phpstan.neon ignore lists.**
-4. If truly impossible (confirmed false positive), use inline ignore with reason.
-5. After fixing, run PHPStan again.
+3. **Do NOT add errors to the baseline or ignore list** (`phpstan-baseline.neon`, `tsconfig.json` `exclude`, `# type: ignore`, `// @ts-ignore`, `#[allow(...)]`, `//nolint`).
+4. If truly impossible (confirmed false positive), use the language-native inline ignore with a one-line reason: `@phpstan-ignore`, `// @ts-expect-error: <reason>`, `# type: ignore[<code>]  # <reason>`, `//nolint:<linter> // <reason>`, `#[allow(<lint>)] // <reason>`.
+5. After fixing, re-run the type-checker.
 6. Repeat until **0 errors**.
 
-### Step 2: Rector — apply automated refactoring
+### Step 2: Auto-fixer / refactoring tool — apply transforms
+
+Run the project's auto-fixer / refactoring tool (skip the step entirely if the project does not ship one):
+- PHP → `vendor/bin/rector process`
+- JS / TS → `npx eslint . --fix` (rule auto-fixes), `npx biome check --apply-unsafe` (safe transforms only)
+- Python → `ruff check . --fix` (lint auto-fixes), `ruff check . --fix --unsafe-fixes` (broader)
+- Go → `golangci-lint run --fix`, `gofmt -w .`, `goimports -w .`
+- Rust → `cargo clippy --fix --allow-dirty --allow-staged`, `cargo fmt`
 
-1. Run Rector with the fix flag.
-2. Review what Rector changed — it may introduce new PHPStan errors.
-3. Run Rector again to verify no further changes are applied.
-4. Repeat until Rector produces no more changes.
+1. Run the auto-fixer with the apply / fix flag.
+2. Review the diff — auto-fixes may introduce new type-checker errors or change semantics on edge cases.
+3. Re-run the auto-fixer to verify it produces no further changes.
+4. Repeat until the auto-fixer is idempotent.
 
-### Step 3: Final PHPStan verification
+### Step 3: Final type-checker verification
 
-1. Run PHPStan one more time.
-2. If new errors appeared (e.g. from Rector changes), fix them as in Step 1.
+1. Run the type-checker (from Step 1) one more time.
+2. If new errors appeared (e.g. from auto-fixer changes), fix them as in Step 1.
 3. If fixes were needed, go back to Step 2.
-4. Done when PHPStan reports **0 errors** and Rector has **no changes**.
+4. Done when the type-checker reports **0 errors** **and** the auto-fixer is idempotent. Also run the formatter once at the very end (`vendor/bin/ecs check --fix` / `prettier --write` / `ruff format` / `cargo fmt`) to normalise whitespace.
 
 ---
 
@@ -105,7 +127,7 @@ git diff --name-only origin/{default}..HEAD
 ## Rules
 
 - **Do NOT commit or push.** Only apply local changes.
-- **Do NOT modify baseline files** (`phpstan-baseline.neon`) or config files (`biome.json`, `tsconfig.json`).
-- **Do NOT add entries to `ignoreErrors`** in `phpstan.neon`.
-- Inline ignores (`@phpstan-ignore`, `@ts-expect-error`, `biome-ignore`) are a last resort.
-- Run `php -l` on modified PHP files if you made significant structural changes.
+- **Do NOT modify baseline files** (`phpstan-baseline.neon`, `tsconfig.json` `exclude`, `.mypy.ini` ignore list, `.eslintrc` `ignorePatterns`, `clippy.toml` `allow` list).
+- **Do NOT widen ignore lists** in the config (`ignoreErrors`, `exclude`, `# type: ignore` blanket, `eslint-disable` file-wide).
+- Inline ignores (`@phpstan-ignore`, `@ts-expect-error`, `# type: ignore[code]`, `biome-ignore`, `eslint-disable-next-line`, `//nolint:`, `#[allow(...)]`) are a last resort and must carry a one-line reason.
+- After significant structural changes, run a language-level syntax check (`php -l <file>`, `node --check <file>`, `python -m py_compile <file>`, `go build ./...`, `cargo check`) before claiming the file is fixed.

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

@@ -1,8 +1,9 @@
 ---
 name: update-form-request-messages
 tier: 2
+framework: laravel
 skills: [laravel-validation]
-description: Sync the messages() method of a FormRequest class — add missing entries, link them to language keys, and clean up stale ones
+description: "Sync the messages() method of a FormRequest class — add missing entries, link them to language keys, and clean up stale ones."
 disable-model-invocation: true
 suggestion:
   eligible: true

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

@@ -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

@@ -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/augment-infrastructure.md

@@ -57,17 +57,14 @@ Define hard constraints: coding standards, Docker usage, language preferences, s
 |---|---|
 | `quality-workflow.md` | PHP (PHPStan → Rector → PHPStan) and JS/TS pipelines |
 | `downstream-changes.md` | After every edit, find and update ALL callers, tests, imports |
-| `docs-sync.md` | Keep docs in sync when skills/rules change |
+| `augment-edit-discipline.md` | Edits inside `.augment/` / `.agent-src.uncompressed/` stay project-agnostic AND sync counts + cross-references in the same edit |
 | `context-hygiene.md` | 3-failure rule, state dumps |
 | `architecture.md` | Architecture principles, file placement |
 | `docker-commands.md` | All PHP commands run inside Docker containers |
 | `commit-conventions.md` | Conventional Commits format |
 | `dev-efficiency.md` | Running CLI commands with verbose output — git, tests, linters, docker, build tools |
-| `e2e-testing.md` | Playwright E2E tests — locators, assertions, Page Objects, CI |
 | `lang-files.md` | Laravel lang files, both de/ and en/ always in sync |
 | `rtk.md` | Using rtk for token-efficient CLI output filtering |
-| `agent-docs.md` | When to read/create/update documentation |
-| `augment-portability.md` | Everything in `.augment/` must be project-agnostic |
 | `roadmap-progress-sync.md` | Checkbox edits in `agents/roadmaps/*.md` must regenerate `agents/roadmaps-progress.md` in the same response |
 
 ### Skills (`.augment/skills/`)
@@ -79,14 +76,14 @@ Skills organized by domain:
 
 | Category | Skills |
 |---|---|
-| **PHP/Laravel** | `php`, `php-coder`, `laravel`, `eloquent`, `laravel-validation`, `php-service`, `dto-creator`, `artisan-commands`, `laravel-horizon`, `laravel-mail`, `laravel-middleware`, `laravel-notifications`, `laravel-pennant`, `laravel-pulse`, `laravel-reverb`, `laravel-scheduling` |
+| **PHP/Laravel** | `php`, `php-coder`, `laravel`, `eloquent`, `laravel-validation`, `php-service`, `laravel-dto`, `artisan-commands`, `laravel-horizon`, `laravel-mail`, `laravel-middleware`, `laravel-notifications`, `laravel-pennant`, `laravel-pulse`, `laravel-reverb`, `laravel-scheduling` |
 | **API** | `api-endpoint`, `api-design`, `api-versioning`, `api-testing`, `openapi` |
 | **Analysis** | `analysis-autonomous-mode`, `universal-project-analysis`, `project-analysis-laravel`, `bug-analyzer`, `security-audit`, `performance-analysis` |
 | **Testing** | `pest-testing`, `test-generator`, `test-performance`, `php-debugging`, `playwright-testing` |
 | **Frontend** | `javascript`, `typescript`, `vue`, `react`, `nextjs`, `nuxt`, `tailwind`, `livewire`, `flux`, `blade-ui`, `fe-design` |
 | **Infrastructure** | `docker`, `aws-infrastructure`, `terraform`, `terragrunt`, `devcontainer`, `github-ci`, `cloudflare-workers`, `traefik` |
-| **Data** | `database`, `migration-creator`, `multi-tenancy`, `performance`, `sql-writing` |
-| **Jobs/Events** | `jobs-events`, `logging-monitoring`, `grafana`, `websocket` |
+| **Data** | `database`, `laravel-migration`, `multi-tenancy`, `performance`, `sql-writing` |
+| **Jobs/Events** | `jobs-events`, `logging-monitoring`, `grafana`, `laravel-websocket` |
 | **Packages** | `composer`, `composer-packages`, `npm`, `npm-packages` |
 | **Design** | `dashboard-design`, `design-review`, `fe-design` |
 | **Agent System** | `agent-docs-writing`, `agents-audit`, `context-create`, `commands`, `copilot-config`, `copilot-agents-optimization`, `feature-planning`, `file-editor`, `guidelines`, `mcp`, `override-management`, `project-docs`, `roadmap-management`, `module-management`, `naming`, `project-analyzer`, `sequential-thinking`, `skill-reviewer` |

package/.agent-src/contexts/communication/rules-auto/guidelines-mechanics.md

@@ -33,7 +33,7 @@ before writing or reviewing code); this file is the catalog.
 | `performance.md` | Performance conventions — caching, Redis, eager loading, response time targets |
 | `security.md` | Security conventions — auth, authorization, SQL injection, XSS, CSRF, headers |
 | `sql.md` | Raw SQL conventions — parameterization, MariaDB syntax, common mistakes |
-| `websocket.md` | WebSocket conventions — Broadcasting, channel types, connection management |
+| `laravel-websocket.md` | Laravel Broadcasting conventions — channel types, connection management, Echo client |
 | `patterns.md` | Design patterns index (links to `patterns/` subdirectory) |
 
 ## PHP Patterns (`docs/guidelines/php/patterns/`)

package/.agent-src/contexts/contracts/research-schema.md

@@ -103,7 +103,7 @@ properties:
 Upstream (`Weizhena/Deep-Research-skills`) shipped a `validate_json.py`
 Pydantic-based validator that assumed `~/.claude/` paths and a Python
 runtime in the consumer environment. Both are
-`augment-portability` violations for this package (zero-runtime-Python
+`augment-edit-discipline` violations for this package (zero-runtime-Python
 goal, host-agnostic distribution). The schema reference above lets the
 agent validate by reading; consumers needing programmatic validation
 can pipe the YAML through any JSON-Schema validator they prefer

package/.agent-src/contexts/execution/interrupt-examples.md

@@ -0,0 +1,34 @@
+# Interrupt Examples — Non-Interrupts, Failure Modes
+
+Loaded by the [`user-interrupt-priority`](../../rules/user-interrupt-priority.md)
+rule when concrete examples sharpen a classification call. The Iron
+Law, classification table, and stop-ask-resume protocol live in the
+rule itself.
+
+## What does NOT count as an interrupt
+
+- **Clarifying question about the current task** — answer in place,
+  keep going.
+- **Quoted text / code / log content** containing imperative verbs
+  ("stop", "abort") — content, not instruction. Speech-act check, same
+  as [`autonomous-execution § opt-in detection`](../../rules/autonomous-execution.md#opt-in-detection--match-by-intent-not-exact-string).
+- **User pasting an error or screenshot** without a redirect —
+  diagnostic input for the current task.
+- **"Why are you doing X?"** as a question — answer it, then continue
+  (unless the answer reveals the current task is wrong, in which case
+  STOP and confirm).
+
+## Failure modes
+
+- **Silent-resume** — treated the interrupt as a pause, returned to the
+  old task without asking. Iron Law violation.
+- **Partial-execution-then-resume** — answered the new ask in two
+  sentences, then went back to the old task without completing the new
+  one. Treat meta-tasks (process audits, council consultations, rule
+  changes) as full tasks, not as quick acknowledgments.
+- **Greedy-bundling** — appended the new task to the old task's plan
+  and continued the old plan first. New task runs **first**, alone, in
+  full.
+- **Autonomy-as-cover** — "user said autonomy on, so I just continued"
+  — autonomy never overrides a fresh instruction. See
+  [`autonomous-execution § Task-scope`](../../rules/autonomous-execution.md).

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

@@ -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/contexts/skills-and-commands.md

@@ -95,13 +95,13 @@ Commands often chain together. Here are the main workflows:
 | Area | Skills |
 |---|---|
 | API endpoints | `api-endpoint`, `api-design`, `api-versioning`, `api-testing`, `openapi`, `laravel-validation` |
-| Database | `eloquent`, `database`, `migration-creator`, `multi-tenancy`, `sql-writing` |
+| Database | `eloquent`, `database`, `laravel-migration`, `multi-tenancy`, `sql-writing` |
 | Background jobs | `jobs-events`, `laravel-horizon`, `laravel-scheduling`, `performance` |
 | Email/Notifications | `laravel-mail`, `laravel-notifications` |
 | Middleware/Auth | `laravel-middleware`, `security` |
 | Feature flags | `laravel-pennant` |
 | Monitoring | `laravel-pulse`, `logging-monitoring`, `grafana`, `sentry-integration` |
-| Real-time | `laravel-reverb`, `websocket` |
+| Real-time | `laravel-reverb`, `laravel-websocket` |
 | Testing | `pest-testing`, `test-generator`, `playwright-testing` |
 | Frontend | `livewire`, `flux`, `blade-ui`, `tailwind`, `vue`, `react`, `fe-design` |
 | Infrastructure | `docker`, `aws-infrastructure`, `terraform`, `terragrunt`, `cloudflare-workers`, `traefik` |

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

@@ -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

@@ -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

@@ -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

@@ -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"