@event4u/agent-config 8.1.0 → 8.3.0

package/README.md

@@ -364,12 +364,21 @@ Three classes of install/runtime behaviour look like package bugs but are host-h
 
 | Tool | Install |
 |---|---|
-| **Augment CLI** · **Claude Code** · **Copilot CLI** | [Install →](docs/installation.md) — rules + skills + commands, marketplace-updated |
+| **Augment CLI** · **Copilot CLI** | [Install →](docs/installation.md) — rules + skills + commands, marketplace-updated |
+
+> **Claude Code: the marketplace plugin is deprecated** (single-surface
+> model). The npx/npm file projection now carries content **and** the
+> deterministic hooks (registered in a managed `~/.claude/settings.json`
+> block by `agent-config global` / `upgrade`), so the plugin only duplicates
+> skill/command listings while its git-SHA snapshot rots silently. Existing
+> installs: `claude plugin uninstall agent-config@event4u-agent-config` —
+> `agent-config doctor` flags the duplicate surface.
 
 Keep the global install current with `agent-config upgrade` (latest) or
 `agent-config refresh --global` (same-version re-install); `agent-config doctor`
-flags a missing-from-`PATH` binary or binary↔plugin version drift. See
-[getting-started § Keeping current](docs/getting-started.md#keeping-current).
+flags a missing-from-`PATH` binary or broken hook wiring. See
+[getting-started § Keeping current](docs/getting-started.md#keeping-current) ·
+[Troubleshooting](#troubleshooting).
 
 ### Cloud / Hosted-agent surfaces
 
@@ -442,6 +451,80 @@ Browse content: [all 166 commands](dist/agent-src/commands/) · [skills catalog]
 
 ---
 
+## Troubleshooting
+
+First stop for any install problem: `agent-config doctor` — it flags a
+missing-from-`PATH` binary, binary↔plugin version drift, stale orphans, and
+manifest issues, each with a one-line fix hint.
+
+### A new command / skill is missing in Claude Code after an upgrade
+
+Under the single-surface model, `agent-config upgrade` refreshes the
+`~/.claude/` file projection — that IS the content surface, so a fresh
+session picks the new commands up directly. If commands are still missing,
+the usual cause is a leftover **marketplace plugin**: it is a git-SHA
+snapshot that never moves with the npm upgrade, and it shadows nothing —
+it just lists everything twice while lagging behind. Remove it:
+
+```bash
+claude plugin uninstall agent-config@event4u-agent-config
+```
+
+Then start a **new** Claude Code session. `agent-config doctor` reports a
+leftover plugin as `claude-plugin: duplicate surface`; hooks are unaffected
+(they live in a managed `~/.claude/settings.json` block — verify with the
+`hook-wiring` check).
+
+### Skills / commands appear twice in Claude Code
+
+Same cause as above: the deprecated marketplace plugin is installed next to
+the `~/.claude/` file projection, so every skill lists plain **and**
+`agent-config:`-prefixed. Uninstall the plugin (command above) and start a
+new session.
+
+### `agent-config upgrade` fails with `Unknown argument: --no-ui`
+
+Known bug in 8.2.0: `upgrade` passed a `--no-ui` flag that the install
+orchestrator did not accept yet, so the run aborted early. Fixed on `main`;
+until the next release, work around it with:
+
+```bash
+AGENT_CONFIG_NO_UI=1 agent-config global   # refresh the global install, no wizard
+```
+
+### Upgrade was interrupted (Ctrl-C, wizard closed, step failed)
+
+Only the initial `npm install -g` hard-aborts an upgrade. Every later step
+(global re-deploy with hook registration, settings sync, wrapper + git-hook
+refresh) runs independently — a single failed step is reported in the
+end-of-run summary instead of silently skipping the rest. Re-run
+`agent-config upgrade` to converge, and use `agent-config doctor` to name
+anything left in a mixed state.
+
+### `agent-config: command not found` / hooks stopped firing
+
+Runtime hooks resolve the **global** binary on `PATH` — a project-local
+install alone is not enough for them. Reinstall the binary:
+
+```bash
+npm install -g @event4u/agent-config
+agent-config doctor   # verifies PATH + plugin wiring
+```
+
+### Project files look stale after a package update
+
+Project-local projections are only rewritten on an explicit refresh:
+
+```bash
+agent-config refresh             # re-apply the installed version to this project
+agent-config refresh --global    # same-version re-install of the global root
+```
+
+More per-version steps: [Migration](docs/MIGRATION.md) ·
+[getting-started § Keeping current](docs/getting-started.md#keeping-current).
+
+---
+
 ## Development
 
 Working on the package itself? Edit `src/` (the source of truth — `src/skills`, `src/rules`, `src/agent-src/`), regenerate trees:

package/dist/agent-src/commands/agents/init.md

@@ -127,13 +127,13 @@ Before writing, scan the generated content for forbidden identifiers:
 - Any project name from `agents/` module docs except the one chosen in 3.1
 - Any reference to vendor-specific internal tools not in the user's stack
 - Any identifier listed in `FORBIDDEN_IDENTIFIERS` in
-  `scripts/check_portability.py` (the package ships a blocklist of
+  `scripts/check_portability.ts` (the package ships a blocklist of
   legacy/adjacent project names that must never leak into consumer files)
 - The package's own name (e.g. the shared-config package itself), unless
   the consumer project explicitly depends on it
 
 If any hit is found, flag it and ask for a replacement. This mirrors what
-`scripts/check_portability.py` enforces for package files.
+`scripts/check_portability.ts` enforces for package files.
 
 ### 6. Write files
 
@@ -179,7 +179,7 @@ contract). On skip, do nothing — the block stays opt-in.
 If `agents/` directory does not exist, suggest running `/optimize agents-dir --scaffold`.
 If `.agent-settings.yml` does not exist, suggest running `scripts/install` (then `/onboard` for first-run setup).
 If module candidates surfaced in Step 7 but the user skipped, note that
-`python3 scripts/propose_modules_config.py` can be re-run anytime.
+`./scripts-run src/scripts/propose_modules_config` can be re-run anytime.
 
 ## Rules
 

package/dist/agent-src/commands/chat-history/import.md

@@ -37,7 +37,7 @@ prior session, see [`/memory mine-session --mode=proposals`](../memory/mine-sess
 ## When NOT to use
 
 - Inspect the current session — use the host's native transcript /
-  session view, or `scripts/chat_history.py read`.
+  session view, or `./scripts-run scripts/chat_history read`.
 - Generate a learning proposal from a prior session — use
   [`/memory mine-session --mode=proposals`](../memory/mine-session/command.md),
   which frames the session's signals and runs `learning-to-rule-or-skill`.
@@ -61,7 +61,7 @@ or the section is missing, say so and stop:
 
 ### 2. List sessions
 
-Run `scripts/chat_history.py sessions --json --limit 20 --summary`.
+Run `./scripts-run scripts/chat_history sessions --json --limit 20 --summary`.
 The helper returns an array of
 `{id, count, first_ts, last_ts, preview, summary}` sorted by
 `last_ts` desc. The `summary` field is built **inside the helper**
@@ -103,7 +103,7 @@ for normal sessions, or `(N entries — no user prompts; t-mix: …)`
 for tool-only sessions). Do **not** truncate or rewrite `summary` —
 markdown table wrap handles long values. Always include an explicit
 `abort` row as the last numbered option. Track option-number → `id`
-internally so step 5 can call `scripts/chat_history.py read
+internally so step 5 can call `./scripts-run scripts/chat_history read
 --session <id>` with the right id.
 
 ### 4. Wait for the pick
@@ -116,7 +116,7 @@ If the user picks the abort option, stop without reading.
 
 ### 5. Read the picked session silently
 
-Run `scripts/chat_history.py read --session <id> --last <count>`,
+Run `./scripts-run scripts/chat_history read --session <id> --last <count>`,
 where `<count>` is the picked row's `count` from step 2. The
 `--last` flag is **required** — the helper defaults to 5 entries,
 which would silently truncate any longer session. The helper returns
@@ -167,6 +167,6 @@ instruction.
 
 - [`/memory mine-session --mode=proposals`](../memory/mine-session/command.md) — pick a prior session and turn it into a project-improving proposal via `learning-to-rule-or-skill` (the former `/chat-history learn`)
 - [`chat-history-platform-hooks`](../../../agents/settings/contexts/chat-history-platform-hooks.md) — read contract, isolation default, opt-in cross-session path
-- [`scripts/chat_history.py`](../../../scripts/chat_history.py) — `sessions` and `read --session` CLI surface
+- [`scripts/chat_history.ts`](../../../scripts/chat_history.ts) — `sessions` and `read --session` CLI surface
 - [`user-interaction`](../../rules/user-interaction.md) — numbered-options Iron Law
 - [`ask-when-uncertain`](../../rules/ask-when-uncertain.md) — one-question-per-turn Iron Law

package/dist/agent-src/commands/chat-history.md

@@ -23,7 +23,7 @@ packs:
 # /chat-history
 
 Top-level orchestrator for the `/chat-history` family. Writes and overflow
-handling are driven entirely by platform hooks + `scripts/chat_history.py`
+handling are driven entirely by platform hooks + `scripts/chat_history.ts`
 internals (`road-to-chat-history-hook-only`); the surfaced sub-command is
 read-only on the cross-host log (`agents/runtime/.agent-chat-history`).
 Sessions coexist in one log file — each entry self-tags via the `s` field —

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

@@ -193,7 +193,7 @@ For every Iron Law section in a source file:
 - **No word-count budget** — condense the prose as hard as telegraph style
   allows. The check is structural (passage count), not quantitative.
 
-`scripts/check_condensation.py` enforces these mechanically — `iron_law_missing`,
+`scripts/check_condensation.ts` enforces these mechanically — `iron_law_missing`,
 `iron_law_passage_dropped`, and `iron_law_heading_downgrade` are `error`-level
 and block CI.
 

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

@@ -38,7 +38,7 @@ Examples:
 
 ### 2. Determine scope (module vs. project-wide)
 
-Resolve module roots via `scripts/_lib/agent_settings.py::enumerate_modules()`
+Resolve module roots via `scripts/_lib/agent_settings.ts::enumerate_modules()`
 (reads `modules.root_paths` + `modules.agent_folder` from
 `.agent-project-settings.yml`). If at least one module is discovered, ask:
 

package/dist/agent-src/commands/council/analysis.md

@@ -71,11 +71,11 @@ Invoke the matching `/council default` form:
 - `prompt:` → `/council default prompt:"<artefact text>"` with
   `--prompt-mode analysis`.
 
-`--prompt-mode` is the CLI flag (`scripts/council_cli.py`) that
+`--prompt-mode` is the CLI flag (`scripts/council_cli.ts`) that
 swaps the lens addendum after the bundler has run. The bundle shape
 stays as the resolved `--input-mode` (prompt | roadmap | files).
 
-The `analysis` mode addendum from `scripts/ai_council/prompts.py`
+The `analysis` mode addendum from `scripts/ai_council/prompts.ts`
 focuses council members on:
 
 - Deduplicating findings restated under different headings.

package/dist/agent-src/commands/council/default.md

@@ -68,7 +68,7 @@ Resolution chain (highest priority first):
 
 Optional **mode_override**: `mode_override=pr|design|optimize` swaps
 the system-prompt addendum for one of the specialised lenses
-(see `prompts.py` `_MODE_TABLE`). The bundle mode is unchanged; only
+(see `prompts.ts` `_MODE_TABLE`). The bundle mode is unchanged; only
 the per-mode neutrality addendum is replaced. Routed by the
 `/council pr`, `/council design`, `/council optimize` sub-commands —
 surface to the user as "council on <target> — <lens> lens".
@@ -171,7 +171,7 @@ redaction, and prints the per-member preview without spending:
 
 `--prompt-mode` is the lens-override flag routed by the
 `/council pr|design|optimize|analysis` wrappers. It swaps the
-per-mode neutrality addendum (see `scripts/ai_council/prompts.py`
+per-mode neutrality addendum (see `scripts/ai_council/prompts.ts`
 `_MODE_TABLE`) without changing the bundle shape. Bare
 `/council default` invocations leave it unset.
 
@@ -321,5 +321,5 @@ council can act on the project directly.
 - `/council` — cluster dispatcher.
 - `ai-council` skill — neutrality guidelines, anti-patterns, redaction expectations.
 - `subagent-orchestration` skill — internal multi-agent variant (no network calls).
-- `scripts/council_cli.py` — the CLI entry point this command wraps.
+- `scripts/council_cli.ts` — the CLI entry point this command wraps.
 - `docs/customization.md` § Available settings → `ai_council.*`.

package/dist/agent-src/commands/council/design.md

@@ -60,10 +60,10 @@ Invoke the matching `/council default` form:
 - `prompt:` → `/council default prompt:"<artefact text>"` with
   `--prompt-mode design`.
 
-`--prompt-mode` is the CLI flag (`scripts/council_cli.py`) that
+`--prompt-mode` is the CLI flag (`scripts/council_cli.ts`) that
 swaps the lens addendum after the bundler has run.
 
-The `design` mode addendum from `scripts/ai_council/prompts.py`
+The `design` mode addendum from `scripts/ai_council/prompts.ts`
 focuses council members on:
 
 - Trust-boundary and module-coupling risk.

package/dist/agent-src/commands/council/optimize.md

@@ -73,7 +73,7 @@ The chosen metric becomes the `original_ask` for the handoff preamble:
 
 Invoke the matching `/council default` form (`files:` / `prompt:`) with
 `--prompt-mode optimize`. The `optimize` mode addendum from
-`scripts/ai_council/prompts.py` requires members to:
+`scripts/ai_council/prompts.ts` requires members to:
 
 - Rank suggestions by expected impact on the chosen metric, not by
   effort or cleverness.

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

@@ -48,7 +48,7 @@ gh pr view <number> --json number,title,body,headRefName,baseRefName,author,url
 
 Capture: title, body, head ref, base ref. The **PR title + body** is
 the user's `original_ask` for the handoff preamble — verbatim, after
-`_strip_host_identity()` cleansing in `prompts.py`. Do **not** add the
+`_strip_host_identity()` cleansing in `prompts.ts`. Do **not** add the
 agent's framing.
 
 ### 3. Fetch the diff range locally
@@ -68,7 +68,7 @@ Invoke `/council default diff:<base>..<head>` with:
 - `original_ask` = PR title + body (capped per
   `bundler.size_guard`; warn if truncated).
 - Pass `--prompt-mode pr` so the neutrality preamble uses the `pr`
-  mode addendum from `scripts/ai_council/prompts.py` — focuses
+  mode addendum from `scripts/ai_council/prompts.ts` — focuses
   members on PR-specific risks (shipping risk, reviewer fatigue,
   scope creep) on top of the generic diff focus (correctness,
   security, tests, maintainability).

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

@@ -44,7 +44,7 @@ Each wrapper resolves its lens-specific input (PR target, design artefact,
 optimization target + metric), captures a wrapper-specific `original_ask`,
 then delegates to `/council default` with `mode_override=<lens>`. The
 lens-specific neutrality addendums live in **one** place —
-[`scripts/ai_council/prompts.py:_MODE_TABLE`](../../scripts/ai_council/prompts.py) —
+[`scripts/ai_council/prompts.ts:_MODE_TABLE`](../../scripts/ai_council/prompts.ts) —
 and are selected by the `mode_override` value. Wrappers never re-implement
 cost-gate, CLI invocation, render, or the host-verdict pass; those flow
 through the master verbatim.

package/dist/agent-src/commands/feature/plan.md

@@ -155,7 +155,7 @@ If no context exists, note this for step 8 (offer to create one after planning).
 
 ### 5b. Determine scope (module vs. project-wide)
 
-Resolve module roots via `scripts/_lib/agent_settings.py::enumerate_modules()`
+Resolve module roots via `scripts/_lib/agent_settings.ts::enumerate_modules()`
 (reads `modules.root_paths` + `modules.agent_folder` from
 `.agent-project-settings.yml`). If at least one module is discovered, ask:
 

package/dist/agent-src/commands/ghostwriter/list.md

@@ -86,7 +86,7 @@ If Step 1 encountered a `fictional: true` file under
     or delete this file.
 ```
 
-This should not normally happen — `scripts/lint_ghostwriter_source.py`
+This should not normally happen — `scripts/lint_ghostwriter_source.ts`
 guards the package side (run via the package's CI), and consumer-side
 `fetch` always writes `fictional: false`.
 

package/dist/agent-src/commands/ghostwriter/write.md

@@ -144,7 +144,7 @@ Non-blocking.
 - **Do NOT commit, push, or open a PR.** The user owns the git surface.
 - **Do NOT omit the disclosure footer.** It is mandatory on every
   invocation. Any flag that would suppress it is forbidden by design
-  and rejected by the package skill linter (`scripts/lint_skills.py`).
+  and rejected by the package skill linter (`scripts/skill_linter.ts`).
 - **Do NOT write the draft to disk.** This command prints only.
 - **Do NOT blend multiple ghostwriter voices.** One style source per
   invocation in v1.

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

@@ -88,7 +88,7 @@ Cluster locked in
 |---|---|---|
 | `agents/reference/ghostwriter/<slug>.md` (consumer) | Real-person public-figure profiles | **No** — gitignored by default. `--shared` opt-in deferred to v2. |
 | `agents/reference/ghostwriter/README.md` (consumer) | Directory anchor + how-to | Yes |
-| `.agent-src.uncondensed/ghostwriter/*.md` (package) | `fictional: true` fixtures only | Yes — CI-enforced by `scripts/lint_ghostwriter_source.py` |
+| `.agent-src.uncondensed/ghostwriter/*.md` (package) | `fictional: true` fixtures only | Yes — CI-enforced by `scripts/lint_ghostwriter_source.ts` |
 
 Slug = full-name kebab-case with optional `-<discriminator>` suffix
 (`alice-walker` vs `alice-walker-novelist`). The package never

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

@@ -8,7 +8,7 @@ replaces: []
 tier: 0
 visibility: visible
 skills: [refine-ticket, feature-planning]
-description: Drive a ticket end-to-end through refine → memory → analyze → plan → implement → test → verify → report — Option-A loop over the `work_engine` Python engine, block-on-ambiguity, no auto-git.
+description: Drive a ticket end-to-end through refine → memory → analyze → plan → implement → test → verify → report — Option-A loop over the `work_engine` engine, block-on-ambiguity, no auto-git.
 suggestion:
   eligible: true
   trigger_description: "implement this ticket, setze ticket X um, build PROJ-123"
@@ -110,7 +110,7 @@ Run the engine with the state file on every iteration:
     [--ticket-file ticket.json --persona <name>]   # first call only
 ```
 
-The dispatcher wires `PYTHONPATH` and routes to the engine module
+The dispatcher resolves the engine module (TypeScript, run via tsx)
 internally. `./agent-config` is the only supported entry point in
 consumer repos — do not call the engine module directly.
 

package/dist/agent-src/commands/judge/on-diff.md

@@ -56,7 +56,7 @@ context. The judge must return one of:
 
 ### 5. Apply or revise
 
-- `apply` → write the diff, run targeted tests, run quality pipeline
+- `apply` → write the diff, run targeted tests; run the quality pipeline only when `quality.local_auto_run: true` (default `false` → skip, remote CI is the gate)
 - `revise` → hand the issue list back to the implementer, loop to step 4
 - `reject` → stop, report to user, do not loop
 

package/dist/agent-src/commands/judge/steps.md

@@ -66,7 +66,9 @@ On stop, report the last verified state so the user can resume.
 ### 5. Final verification
 
 After step N passes judgment, run `verify-completion-evidence` across the
-whole changeset — targeted tests + full suite + quality pipeline.
+whole changeset — targeted tests, plus full suite + quality pipeline only
+when `quality.local_auto_run: true` (default `false` → skip, remote CI is
+the gate; report "quality gates delegated to remote CI").
 Never declare the plan "done" without this gate.
 
 ### 6. Report

package/dist/agent-src/commands/memory/add.md

@@ -31,7 +31,7 @@ the first write and for every subsequent addition.
 ## Prerequisites
 
 - Consumer project has an `agents/` directory (package installed).
-- `scripts/check_memory.py` is available (shipped with the package).
+- `scripts/check_memory.ts` is available (shipped with the package).
 - User can name a concrete pattern — see the "when to reject" section.
 
 ## Steps
@@ -136,7 +136,7 @@ Read `verbosity.post_action_reports` from `.agent-settings.yml` (default
   ```
   ✅  Added <type>/<id> (confidence: <high|medium|low>)
      Path: agents/memory/<type>.yml (or agents/memory/<type>/<hash>.yml)
-     Gate: scripts/check_memory.py → PASS
+     Gate: scripts/check_memory.ts → PASS
      Next: commit and link from the relevant skill/command.
   ```
 

package/dist/agent-src/commands/memory/learn-low-impact.md

@@ -52,7 +52,7 @@ for the eight forbidden-content classes.
 ### 1. Build the preview plan
 
 Call
-`scripts/ai_council/learn_low_impact_preview.py::build_preview` with
+`scripts/ai_council/learn_low_impact_preview.ts::build_preview` with
 the project-local corpus and the package seed:
 
 ```python

package/dist/agent-src/commands/memory/load.md

@@ -81,7 +81,7 @@ for (const f of glob("agents/memory").sort()) {
 The Tier-0 slice is surfaced once per `/memory:load` invocation, even
 when the user picks a type with no critical entries — the slice spans
 types deliberately. Token cost is bounded by the soft cap of 10
-critical entries per type (warned by `scripts/check_memory.py`).
+critical entries per type (warned by `scripts/check_memory.ts`).
 
 ### 2. Warn about volume
 

package/dist/agent-src/commands/memory/mine-session.md

@@ -167,7 +167,7 @@ Confirm:
   reasoning blocks, system reminders) before pattern matching. If the
   miner under-counts, audit the adapter's redact list, not the regex.
 - Date-discipline: relative phrases (`yesterday`, `last week`) in the
-  observation field are rejected by `scripts/check_memory.py` unless
+  observation field are rejected by `scripts/check_memory.ts` unless
   re-anchored with `YYYY-MM-DD` within ±20 chars. The miner re-anchors
   automatically using the turn's `ts`; verify before commit.
 

package/dist/agent-src/commands/memory/promote.md

@@ -21,7 +21,7 @@ packs:
 Moves an entry from the provisional layer (intake JSONL) into the
 curated layer (`agents/memory/<type>.yml` or sharded). Promotion is
 gated by
-[`scripts/check_memory_proposal.py`](../../../scripts/check_memory_proposal.py),
+[`scripts/check_memory_proposal.ts`](../../../scripts/check_memory_proposal.ts),
 which enforces the **pattern-vs-one-off** discipline: either ≥ 2
 distinct paths share the root-cause signature, or the submitter
 supplies ≥ 3 concrete future decisions that will be steered by the

package/dist/agent-src/commands/memory/propose.md

@@ -19,7 +19,7 @@ packs:
 
 # /memory propose
 Drops a **signal** into `agents/memory/intake/signals-YYYY-MM.jsonl` via
-`scripts/memory_signal.py`. Signals are append-only JSONL and merge-safe.
+`scripts/memory_signal.ts`. Signals are append-only JSONL and merge-safe.
 
 Unlike [`/memory-add`](memory-add.md) — which writes a **curated**
 entry the reviewer has validated — `/propose-memory` is cheap and

package/dist/agent-src/commands/mission/upgrade.md

@@ -158,7 +158,7 @@ Per [`scope-control`](../../rules/scope-control.md), git operations are permissi
 
 ## Breaking-change catalog
 
-Knowledge source: `src/missions/upgrade/laravel-10-to-11.yaml`. Versionable, diffable, CI-tested via `lint_missions.py`. Each entry carries:
+Knowledge source: `src/missions/upgrade/laravel-10-to-11.yaml`. Versionable, diffable, CI-tested via `lint_missions.ts`. Each entry carries:
 
 - `id` — unique checkpoint key (used in `.work-state.json`)
 - `severity` — `critical` / `high` / `medium` / `low`

package/dist/agent-src/commands/module/explore.md

@@ -24,12 +24,12 @@ packs:
 ### 1. Resolve module roots
 
 Read the `modules:` block from `.agent-project-settings.yml` via the
-loader (`get_modules_config()` in `scripts/_lib/agent_settings.py`):
+loader (`get_modules_config()` in `scripts/_lib/agent_settings.ts`):
 
 - If `modules.enabled` is `true` and `modules.root_paths` is non-empty,
   use those paths verbatim. Skip the fallback table.
 - If the block is missing / disabled / empty, fall back to the
-  auto-detection table below — same shape `propose_modules_config.py`
+  auto-detection table below — same shape `propose_modules_config.ts`
   uses internally.
 
 **Auto-detection fallback table** (consulted only when `modules:` is
@@ -54,7 +54,7 @@ Stop.
 ### 2. List available modules
 
 Enumerate modules across every resolved root via `enumerate_modules()`
-(see `scripts/_lib/agent_settings.py`). Skip directories listed in
+(see `scripts/_lib/agent_settings.ts`). Skip directories listed in
 `modules.skip_dirs` (defaults: `.module-template`, `.example`) and
 hidden dirs. The "Agent Docs" column reflects the configured
 `modules.agent_folder` (default `agents/`):

package/dist/agent-src/commands/optimize/agents-dir.md

@@ -58,7 +58,7 @@ surface changes.
 
 1. **Verify project root** — look for `composer.json`, `artisan`, or `package.json`.
 2. **Create directory structure** — `agents/{roadmaps,features,contexts}/.gitkeep` + `.augment/guidelines/php/.gitkeep`. Skip dirs that already exist with content.
-3. **Module support** — resolve module roots via `scripts/_lib/agent_settings.py::enumerate_modules()`. For every discovered module, mirror the layout: `{module_root}/{Module}/{agent_folder}/{roadmaps,features,contexts}/.gitkeep` (Laravel example: `app/Modules/{Module}/agents/{roadmaps,features,contexts}/.gitkeep`). Skip when `modules.enabled: false` or no roots configured.
+3. **Module support** — resolve module roots via `scripts/_lib/agent_settings.ts::enumerate_modules()`. For every discovered module, mirror the layout: `{module_root}/{Module}/{agent_folder}/{roadmaps,features,contexts}/.gitkeep` (Laravel example: `app/Modules/{Module}/agents/{roadmaps,features,contexts}/.gitkeep`). Skip when `modules.enabled: false` or no roots configured.
 4. **Verify templates** — confirm `.augment/templates/{features,roadmaps,contexts}.md` exist; warn on missing.
 5. **Clean up old templates** — offer to delete legacy `agents/features/template.md` etc. (now in `.augment/templates/`); ask before delete.
 6. **Show summary** — table with status per directory and template; flag missing as `⚠️`.

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

@@ -129,5 +129,5 @@ If any check fails: do NOT suggest the change.
 - **No quality judgments** — the skill linter and `skill-reviewer` handle that
 - **No auto-fixes** — all changes require explicit user approval
 - **No "make it shorter"** — condensation is done by Telegraph Condensation, not here
-- **No Killer checks** — replaced by the skill linter (`scripts/skill_linter.py`)
+- **No Killer checks** — replaced by the skill linter (`scripts/skill_linter.ts`)
 - **No edits to `dist/agent-src/` or `.augment/`** — always edit `.agent-src.uncondensed/`, then sync

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

@@ -62,7 +62,7 @@ audit (route to `/analyze:decision`), code-only analysis
      installed agent layer. Surface = workflows, structures, docs,
      roadmaps, decisions.
 2. Resolve module roots via
-   `scripts/_lib/agent_settings.py::enumerate_modules()` (Laravel shape:
+   `scripts/_lib/agent_settings.ts::enumerate_modules()` (Laravel shape:
    `app/Modules/*/agents/`); fallback `modules.root_paths` in
    `.agent-settings.yml`.
 3. Exclusions hard: never analyze `vendor/`, `node_modules/`, `dist/`,

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

@@ -28,7 +28,7 @@ personas, skills, commands, and sub-agents pinned by the
 contract.
 
 This command is the **runtime** side of the contract. The schema and
-the linter (`scripts/lint_orchestration_dsl.py`) live on the authoring
+the linter (`scripts/lint_orchestration_dsl.ts`) live on the authoring
 side; this command reads the same shape and dispatches each step.
 
 ### 1. Resolve the pipeline file
@@ -125,6 +125,6 @@ output body.
 ## See also
 
 - Contract: [`orchestration-dsl-v1.md`](../docs/contracts/orchestration-dsl-v1.md)
-- Linter: `scripts/lint_orchestration_dsl.py`
+- Linter: `scripts/lint_orchestration_dsl.ts`
 - Subagent runtime: [`subagent-orchestration`](../skills/subagent-orchestration/SKILL.md)
 - Audit emission: [`audit-log-v1.md`](../docs/contracts/audit-log-v1.md)

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

@@ -31,7 +31,7 @@ Gather in parallel:
 - Check for: `artisan`, `Makefile`, `Taskfile.yml`, `docker-compose.yml`
 - Check for: `phpstan.neon`, `ecs.php`, `rector.php`, `config-dev/`
 - Check for: `.github/workflows/`, `CODEOWNERS`, `.editorconfig`
-- Check for module roots (resolve via `scripts/_lib/agent_settings.py::enumerate_modules()`; Laravel shape: `app/Modules/`), multi-tenant indicators (`customer_database`)
+- Check for module roots (resolve via `scripts/_lib/agent_settings.ts::enumerate_modules()`; Laravel shape: `app/Modules/`), multi-tenant indicators (`customer_database`)
 - Read: `AGENTS.md`, `.github/copilot-instructions.md` (if exist)
 
 Display:

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

@@ -29,7 +29,7 @@ Run in parallel:
 - `git branch --show-current` → current branch
 - `git log --oneline -3` → recent activity
 - Count files in `agents/` (docs, features, roadmaps, contexts)
-- Resolve modules via `scripts/_lib/agent_settings.py::enumerate_modules()`
+- Resolve modules via `scripts/_lib/agent_settings.ts::enumerate_modules()`
 - For every module: count files in `{module_path}/{modules.agent_folder}/` (Laravel shape: `app/Modules/*/agents/`)
 - Module list comes from `enumerate_modules()` (Laravel shape: `app/Modules/`)
 - Count test files

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

@@ -187,4 +187,4 @@ It does **NOT**:
 - [`/roadmap`](../roadmap.md) — cluster orchestrator
 - [`/council default`](../council/default.md) — base flow this command wraps
 - [`ai-council`](../../skills/ai-council/SKILL.md) — neutrality, redaction, deep tier
-- [`scripts/council_cli.py`](../../../scripts/council_cli.py) — CLI entry point
+- [`scripts/council_cli.ts`](../../../scripts/council_cli.ts) — CLI entry point

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

@@ -29,7 +29,7 @@ Ask the user (in their language) where the roadmap should be created:
 > 2. In a module (`{module_root}/{Name}/{agent_folder}/roadmaps/`)
 
 If the user picks a module → resolve module roots via
-`scripts/_lib/agent_settings.py::enumerate_modules()`, list available
+`scripts/_lib/agent_settings.ts::enumerate_modules()`, list available
 modules from `modules.root_paths`, and ask which one. The target
 directory is `{module_path}/{modules.agent_folder}/roadmaps/`
 (default `agent_folder` = `agents`).
@@ -184,7 +184,7 @@ If the user picks **1**:
 
 - Run `/council roadmap:<path>` with the user's original ask captured
   in step 1 as `original_ask` (the handoff preamble carries it
-  verbatim, see `scripts/ai_council/prompts.py`).
+  verbatim, see `scripts/ai_council/prompts.ts`).
 - Append the council findings as a `## Council review (<UTC date>)`
   section at the bottom of the roadmap. Include the trace path to
   `agents/runtime/council/sessions/<timestamp>/raw-text.md` so future readers

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

@@ -53,7 +53,9 @@ with the **scope delta below**.
   security-sensitive, scope-out-of-roadmap, test/quality red).
 - **Phase boundary handling:** at every phase boundary, run the
   per-phase quality pipeline when `quality_cadence: per_phase` (or
-  `per_step`). On red → stop, surface, do **not** silently roll into
+  `per_step`) AND `quality.local_auto_run: true` — under the default
+  (`false` / missing) the pipeline never runs locally; remote CI is
+  the gate. On red → stop, surface, do **not** silently roll into
   the next phase. Under `mode: phase-checkpoints`, additionally emit
   the compact status + continue prompt at every boundary; under
   `autonomous`, boundaries are silent (quality pipeline aside).

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

@@ -52,8 +52,10 @@ branching, halt conditions, and the archival check.
   phase. Use [`/roadmap:process-full`](process-full.md) for continuous
   execution across phases.
 - **Quality cadence at the boundary:** run the per-phase pipeline when
-  `quality_cadence: per_phase` (or `per_step`). Skip when
-  `end_of_roadmap`.
+  `quality_cadence: per_phase` (or `per_step`) AND
+  `quality.local_auto_run: true`. Skip when `end_of_roadmap` — and
+  always skip under the default (`local_auto_run` `false` / missing);
+  remote CI is the gate.
 
 ## Rules
 

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

@@ -45,7 +45,9 @@ with the **scope delta below**.
   [`roadmap-process-loop § 5`](../../contexts/execution/roadmap-process-loop.md#5-step-loop)
   (sub-steps 1–7). After the checkbox edit + dashboard regen, **stop**.
 - **Quality cadence:** run the per-step pipeline only when
-  `quality_cadence: per_step`. Skip otherwise.
+  `quality_cadence: per_step` AND `quality.local_auto_run: true`.
+  Skip otherwise — under the default (`false` / missing) remote CI
+  is the gate.
 - **Phase boundary:** if this single step happens to close the phase,
   do **not** advance. Report the phase as complete and stop.
 - **Roadmap boundary:** if this single step happens to close the