@lifeaitools/rdc-skills 0.24.38 → 0.24.41

package/skills/watch/SKILL.md

@@ -1,97 +1,97 @@
----
-name: rdc:watch
-description: "Usage `rdc:watch` — Initialize a live session-log viewer and report its path; open it only during attended, non-test use. Zero infrastructure — pure filesystem + static HTML."
----
-
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
-> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
-
-> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
-
-
-# rdc:watch — Session Log Watcher
-
-## When to Use
-- Start of any long-running session where Dave needs visibility into what you're doing
-- Before `rdc:overnight`, `rdc:build` on a large epic, or any multi-hour grind
-- Anytime the user asks for "a log", "a viewer", "tail", or "what are you doing right now"
-
-## Procedure
-
-1. **Initialize the log and viewer.** Run the helper script from the plugin directory in the user's current project:
-   ```bash
-   node ${CLAUDE_PLUGIN_ROOT}/scripts/watch-init.mjs
-   ```
-   (If `CLAUDE_PLUGIN_ROOT` is not set, resolve the plugin path from your invocation context or the installed plugin cache.)
-
-2. **Parse the output.** The script prints `run_id`, `log_path`, `current`, `viewer`, and `open_hint`. Capture `log_path` and `viewer` for the rest of the session.
-
-3. **Open the viewer in the browser, unless running under `RDC_TEST=1`.**
-   - Normal attended use: run the exact `open_hint` line from the script output. On Windows that's `start "" "<viewer-path>"`.
-   - `RDC_TEST=1`: do not run `open_hint`, `start`, `open`, `xdg-open`, or any focus/window API. Report the viewer path only.
-
-4. **Report to the user.** One line:
-   ```
-   watcher live at <viewer-path> — tailing <log-path>
-   ```
-   In `RDC_TEST=1`, say:
-   ```
-   watcher initialized at <viewer-path> — not opened because RDC_TEST=1
-   ```
-
-5. **Append one line per substantive action for the rest of the session.** Use the documented format — one line, no multi-line payloads:
-   ```
-   [<ISO-timestamp>] [<kind>] <message>
-   ```
-   Append to BOTH `<log-path>` (the full history) AND `current.log` (what the viewer polls). The viewer diffs `current.log` by length and only appends new lines.
-
-### Log format
-
-- `ISO-timestamp` — `new Date().toISOString()`
-- `kind` — one of: `dispatch`, `commit`, `test`, `error`, `note`, `banner`
-- `message` — single line, no newlines. Keep under ~200 chars.
-
-### Kinds
-
-| Kind | When to append |
-|------|----------------|
-| `dispatch` | About to dispatch a subagent — include role + epic/task id |
-| `commit` | After a git commit lands — include short sha + subject |
-| `test` | Test run kicked off or result came back |
-| `error` | Anything that failed — include what and why in one line |
-| `note` | General progress ticks (reading files, analyzing, planning) |
-| `banner` | Session start/end markers, major phase changes |
-
-### Examples
-
-```
-[2026-04-15T23:14:02.318Z] [dispatch] frontend agent → epic abc123 task 4 (rebuild DynamicForm)
-[2026-04-15T23:17:41.902Z] [commit] 3f2a1b9 feat(marketing-engine): DynamicForm rhf+zod
-[2026-04-15T23:18:05.113Z] [test] pnpm --filter @regen/rdc-marketing-engine test
-[2026-04-15T23:18:41.002Z] [error] tsc: src/components/Form.tsx:42 — Property 'foo' does not exist
-[2026-04-15T23:19:00.000Z] [note] retrying with corrected type import
-[2026-04-15T23:45:10.000Z] [banner] Phase 2 complete — moving to review
-```
-
-### Appending from bash (Windows-safe)
-
-```bash
-printf '[%s] [%s] %s\n' "$(date -u +%Y-%m-%dT%H:%M:%S.000Z)" "dispatch" "your message" >> "$LOG_PATH"
-printf '[%s] [%s] %s\n' "$(date -u +%Y-%m-%dT%H:%M:%S.000Z)" "dispatch" "your message" >> "$CURRENT_PATH"
-```
-
-Or from Node:
-```js
-import { appendFileSync } from "node:fs";
-const line = `[${new Date().toISOString()}] [note] ${msg}\n`;
-appendFileSync(logPath, line);
-appendFileSync(currentPath, line);
-```
-
-## Notes
-
-- Log files live in the **user's project**, not the rdc-skills repo. Path: `<projectRoot>/.rdc/session-log/`
-- Each invocation creates a **new run id** and overwrites `current.log`. Prior run logs remain on disk as `<runId>.log`.
-- The viewer is a single static HTML file polling `current.log` via `fetch()` every 2s — no server, no deps.
-- This skill does NOT replace `rdc:report` (the end-of-session Obsidian writeup). It's a live tail for attended or semi-attended sessions.
+---
+name: rdc:watch
+description: "Usage `rdc:watch` — Initialize a live session-log viewer and report its path; open it only during attended, non-test use. Zero infrastructure — pure filesystem + static HTML."
+---
+
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
+
+
+# rdc:watch — Session Log Watcher
+
+## When to Use
+- Start of any long-running session where Dave needs visibility into what you're doing
+- Before `rdc:overnight`, `rdc:build` on a large epic, or any multi-hour grind
+- Anytime the user asks for "a log", "a viewer", "tail", or "what are you doing right now"
+
+## Procedure
+
+1. **Initialize the log and viewer.** Run the helper script from the plugin directory in the user's current project:
+   ```bash
+   node ${CLAUDE_PLUGIN_ROOT}/scripts/watch-init.mjs
+   ```
+   (If `CLAUDE_PLUGIN_ROOT` is not set, resolve the plugin path from your invocation context or the installed plugin cache.)
+
+2. **Parse the output.** The script prints `run_id`, `log_path`, `current`, `viewer`, and `open_hint`. Capture `log_path` and `viewer` for the rest of the session.
+
+3. **Open the viewer in the browser, unless running under `RDC_TEST=1`.**
+   - Normal attended use: run the exact `open_hint` line from the script output. On Windows that's `start "" "<viewer-path>"`.
+   - `RDC_TEST=1`: do not run `open_hint`, `start`, `open`, `xdg-open`, or any focus/window API. Report the viewer path only.
+
+4. **Report to the user.** One line:
+   ```
+   watcher live at <viewer-path> — tailing <log-path>
+   ```
+   In `RDC_TEST=1`, say:
+   ```
+   watcher initialized at <viewer-path> — not opened because RDC_TEST=1
+   ```
+
+5. **Append one line per substantive action for the rest of the session.** Use the documented format — one line, no multi-line payloads:
+   ```
+   [<ISO-timestamp>] [<kind>] <message>
+   ```
+   Append to BOTH `<log-path>` (the full history) AND `current.log` (what the viewer polls). The viewer diffs `current.log` by length and only appends new lines.
+
+### Log format
+
+- `ISO-timestamp` — `new Date().toISOString()`
+- `kind` — one of: `dispatch`, `commit`, `test`, `error`, `note`, `banner`
+- `message` — single line, no newlines. Keep under ~200 chars.
+
+### Kinds
+
+| Kind | When to append |
+|------|----------------|
+| `dispatch` | About to dispatch a subagent — include role + epic/task id |
+| `commit` | After a git commit lands — include short sha + subject |
+| `test` | Test run kicked off or result came back |
+| `error` | Anything that failed — include what and why in one line |
+| `note` | General progress ticks (reading files, analyzing, planning) |
+| `banner` | Session start/end markers, major phase changes |
+
+### Examples
+
+```
+[2026-04-15T23:14:02.318Z] [dispatch] frontend agent → epic abc123 task 4 (rebuild DynamicForm)
+[2026-04-15T23:17:41.902Z] [commit] 3f2a1b9 feat(marketing-engine): DynamicForm rhf+zod
+[2026-04-15T23:18:05.113Z] [test] pnpm --filter @regen/rdc-marketing-engine test
+[2026-04-15T23:18:41.002Z] [error] tsc: src/components/Form.tsx:42 — Property 'foo' does not exist
+[2026-04-15T23:19:00.000Z] [note] retrying with corrected type import
+[2026-04-15T23:45:10.000Z] [banner] Phase 2 complete — moving to review
+```
+
+### Appending from bash (Windows-safe)
+
+```bash
+printf '[%s] [%s] %s\n' "$(date -u +%Y-%m-%dT%H:%M:%S.000Z)" "dispatch" "your message" >> "$LOG_PATH"
+printf '[%s] [%s] %s\n' "$(date -u +%Y-%m-%dT%H:%M:%S.000Z)" "dispatch" "your message" >> "$CURRENT_PATH"
+```
+
+Or from Node:
+```js
+import { appendFileSync } from "node:fs";
+const line = `[${new Date().toISOString()}] [note] ${msg}\n`;
+appendFileSync(logPath, line);
+appendFileSync(currentPath, line);
+```
+
+## Notes
+
+- Log files live in the **user's project**, not the rdc-skills repo. Path: `<projectRoot>/.rdc/session-log/`
+- Each invocation creates a **new run id** and overwrites `current.log`. Prior run logs remain on disk as `<runId>.log`.
+- The viewer is a single static HTML file polling `current.log` via `fetch()` every 2s — no server, no deps.
+- This skill does NOT replace `rdc:report` (the end-of-session Obsidian writeup). It's a live tail for attended or semi-attended sessions.

package/skills/workitems/SKILL.md

@@ -1,151 +1,151 @@
----
-name: rdc:workitems
-description: "Usage `rdc:workitems [add|done|status|list|query]` — Manual work item CRUD outside the normal build flow: add to backlog, mark done, update status, list open epics, query by label."
----
-
-> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
-> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
-> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
-
-> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
-
-> **Sandbox contract:** This skill honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag. Supabase work item writes (`insert_work_item`, `update_work_item_status`, `bump_epic_version`) are skipped under `RDC_TEST=1`.
-
-
-# rdc:workitems — Work Item Management
-
-## When to Use
-- Project lead says "create a ticket", "add to backlog", "log this bug", "update status"
-- An agent needs to create or update epics/tasks during a build session
-- Checking what work is open before starting a new epic
-
-## Arguments
-
-- `rdc:workitems epics` — list open epics
-- `rdc:workitems add <title> --epic <id>` — create a task under an epic
-- `rdc:workitems update <id> --status <status>` — update a work item's status
-- `rdc:workitems done <id>` — mark a task complete
-- `rdc:workitems list <epic-id>` — list tasks in an epic
-
-## Rules
-
-1. **Epic first, always.** Never create a task without a parent epic.
-2. **Label everything.** Minimum one system label per item.
-3. **Check first.** `get_open_epics()` before creating anything new.
-4. **Link design docs.** Put `.rdc/plans/` or `.rdc/research/` paths in descriptions (fallback: `.rdc/plans/` / `.rdc/research/`).
-
-## Read Epics
-
-```sql
-SELECT get_open_epics();
-SELECT get_open_epics('urgent');
-SELECT get_open_epics(p_label_filter := 'custom-label');
-```
-
-## Create Epic
-
-```sql
-SELECT insert_work_item(
-  p_title       := 'EPIC: Clear descriptive title',
-  p_description := 'What and why. Reference .rdc/plans/<n>.md if applicable.',
-  p_item_type   := 'epic',
-  p_priority    := 'high',
-  p_labels      := ARRAY['system-label'],
-  p_source      := 'planning'
-);
-```
-
-## Create Task
-
-```sql
-SELECT insert_work_item(
-  p_title       := 'Specific actionable task title',
-  p_description := 'What: <deliverable>
-Where: <files to create/modify>
-Agent type: frontend | backend | data | design | infra | content | cs2
-Guide: .rdc/guides/<type>.md (fallback: .rdc/guides/<type>.md)
-Design doc: .rdc/plans/<n>.md (fallback: .rdc/plans/<n>.md, if exists)
-Depends on: <other task title if sequential>
-Est: <hours>',
-  p_parent_id   := '<epic-uuid>'::uuid,
-  p_item_type   := 'task',
-  p_priority    := 'high',
-  p_labels      := ARRAY['system-label'],
-  p_estimated_hours := 2,
-  p_source      := 'planning'
-);
-```
-
-## Update Status
-
-```sql
-SELECT update_work_item_status('<uuid>'::uuid, 'in_progress');
-SELECT update_work_item_status('<uuid>'::uuid, 'review', '["Implementation complete; ready for validator"]'::jsonb, '<agent-session-id>', 'agent');
-SELECT update_work_item_status('<uuid>'::uuid, 'done', '["Validator verified implementation report, CodeFlow post, and checklist evidence"]'::jsonb, '<validator-session-id>', 'validator');
-SELECT update_work_item_status('<uuid>'::uuid, 'blocked', '["Why it is blocked"]'::jsonb);
-```
-
-Non-epic `done` is a validator-only close and requires an existing
-`implementation_report.codeflow_post`, checked required checklist evidence, and
-originating-agent tick audit.
-
-## Read Tasks in an Epic
-
-```sql
-SELECT get_work_items_by_epic('<epic-uuid>'::uuid);
-SELECT get_work_items_by_epic('<epic-uuid>'::uuid, 'todo');
-```
-
-## Bump Epic Version
-
-```sql
-SELECT bump_epic_version('<epic-uuid>'::uuid, '0.2.0', 'What changed', 'planning');
-```
-
-## Valid Values
-
-| Field | Values |
-|-------|--------|
-| status | `todo` `in_progress` `blocked` `review` `done` `archived` |
-| priority | `urgent` `high` `normal` `low` |
-| item_type | `epic` `task` `subtask` `bug` `spike` |
-
-## System Labels
-
-| Label | When |
-|-------|------|
-| `project-a` | Your-app-specific work |
-| `project-b` | Another app work |
-| `cs2` | Core paradigm packages |
-| `hail` | Grammar, DSL compiler |
-| `pal` | Moment windows, memory |
-| `virtue` | Virtue engine, coherence |
-| `marketing` | Outreach, campaigns |
-| `media` | Assets, R2, image pipeline |
-| `infrastructure` | CI/CD, deployment |
-| `ui` | Component library |
-| `data` | Schema, migrations |
-| `content` | Copy, messaging |
-| `website` | Public-facing sites |
-
-## Agent Type → Guide File Reference
-
-| Type | Guide | Use For |
-|------|-------|---------|
-| `frontend` | .rdc/guides/frontend.md | React, pages, UI, Tailwind |
-| `backend` | .rdc/guides/backend.md | API routes, database, auth |
-| `data` | .rdc/guides/data.md | Migrations, schema, RPC |
-| `design` | .rdc/guides/design.md | Brand, palette, OG images |
-| `infra` | .rdc/guides/infrastructure.md | CI/CD, deploy, DNS |
-| `content` | .rdc/guides/content.md | Copy, messaging, tone |
-| `cs2` | .rdc/guides/cs2.md | CS 2.0 paradigm |
-| `hail` | .rdc/guides/cs2.md + packages/hail/CLAUDE.md | Grammar, DSL |
-| `viz` | .rdc/guides/frontend.md + design.md | Custom visualizations |
-
-## What NOT to Do
-
-- Never raw INSERT/UPDATE against work items — RPC functions only
-- Never create tasks without a parent epic
-- Never leave labels empty
-- Never write vague titles ("Fix stuff") — be specific
-- Never put design intention in the task — put it in `.rdc/research/` (fallback: `.rdc/research/`) and link
+---
+name: rdc:workitems
+description: "Usage `rdc:workitems [add|done|status|list|query]` — Manual work item CRUD outside the normal build flow: add to backlog, mark done, update status, list open epics, query by label."
+---
+
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
+
+> **Sandbox contract:** This skill honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag. Supabase work item writes (`insert_work_item`, `update_work_item_status`, `bump_epic_version`) are skipped under `RDC_TEST=1`.
+
+
+# rdc:workitems — Work Item Management
+
+## When to Use
+- Project lead says "create a ticket", "add to backlog", "log this bug", "update status"
+- An agent needs to create or update epics/tasks during a build session
+- Checking what work is open before starting a new epic
+
+## Arguments
+
+- `rdc:workitems epics` — list open epics
+- `rdc:workitems add <title> --epic <id>` — create a task under an epic
+- `rdc:workitems update <id> --status <status>` — update a work item's status
+- `rdc:workitems done <id>` — mark a task complete
+- `rdc:workitems list <epic-id>` — list tasks in an epic
+
+## Rules
+
+1. **Epic first, always.** Never create a task without a parent epic.
+2. **Label everything.** Minimum one system label per item.
+3. **Check first.** `get_open_epics()` before creating anything new.
+4. **Link design docs.** Put `.rdc/plans/` or `.rdc/research/` paths in descriptions (fallback: `.rdc/plans/` / `.rdc/research/`).
+
+## Read Epics
+
+```sql
+SELECT get_open_epics();
+SELECT get_open_epics('urgent');
+SELECT get_open_epics(p_label_filter := 'custom-label');
+```
+
+## Create Epic
+
+```sql
+SELECT insert_work_item(
+  p_title       := 'EPIC: Clear descriptive title',
+  p_description := 'What and why. Reference .rdc/plans/<n>.md if applicable.',
+  p_item_type   := 'epic',
+  p_priority    := 'high',
+  p_labels      := ARRAY['system-label'],
+  p_source      := 'planning'
+);
+```
+
+## Create Task
+
+```sql
+SELECT insert_work_item(
+  p_title       := 'Specific actionable task title',
+  p_description := 'What: <deliverable>
+Where: <files to create/modify>
+Agent type: frontend | backend | data | design | infra | content | cs2
+Guide: .rdc/guides/<type>.md (fallback: .rdc/guides/<type>.md)
+Design doc: .rdc/plans/<n>.md (fallback: .rdc/plans/<n>.md, if exists)
+Depends on: <other task title if sequential>
+Est: <hours>',
+  p_parent_id   := '<epic-uuid>'::uuid,
+  p_item_type   := 'task',
+  p_priority    := 'high',
+  p_labels      := ARRAY['system-label'],
+  p_estimated_hours := 2,
+  p_source      := 'planning'
+);
+```
+
+## Update Status
+
+```sql
+SELECT update_work_item_status('<uuid>'::uuid, 'in_progress');
+SELECT update_work_item_status('<uuid>'::uuid, 'review', '["Implementation complete; ready for validator"]'::jsonb, '<agent-session-id>', 'agent');
+SELECT update_work_item_status('<uuid>'::uuid, 'done', '["Validator verified implementation report, CodeFlow post, and checklist evidence"]'::jsonb, '<validator-session-id>', 'validator');
+SELECT update_work_item_status('<uuid>'::uuid, 'blocked', '["Why it is blocked"]'::jsonb);
+```
+
+Non-epic `done` is a validator-only close and requires an existing
+`implementation_report.codeflow_post`, checked required checklist evidence, and
+originating-agent tick audit.
+
+## Read Tasks in an Epic
+
+```sql
+SELECT get_work_items_by_epic('<epic-uuid>'::uuid);
+SELECT get_work_items_by_epic('<epic-uuid>'::uuid, 'todo');
+```
+
+## Bump Epic Version
+
+```sql
+SELECT bump_epic_version('<epic-uuid>'::uuid, '0.2.0', 'What changed', 'planning');
+```
+
+## Valid Values
+
+| Field | Values |
+|-------|--------|
+| status | `todo` `in_progress` `blocked` `review` `done` `archived` |
+| priority | `urgent` `high` `normal` `low` |
+| item_type | `epic` `task` `subtask` `bug` `spike` |
+
+## System Labels
+
+| Label | When |
+|-------|------|
+| `project-a` | Your-app-specific work |
+| `project-b` | Another app work |
+| `cs2` | Core paradigm packages |
+| `hail` | Grammar, DSL compiler |
+| `pal` | Moment windows, memory |
+| `virtue` | Virtue engine, coherence |
+| `marketing` | Outreach, campaigns |
+| `media` | Assets, R2, image pipeline |
+| `infrastructure` | CI/CD, deployment |
+| `ui` | Component library |
+| `data` | Schema, migrations |
+| `content` | Copy, messaging |
+| `website` | Public-facing sites |
+
+## Agent Type → Guide File Reference
+
+| Type | Guide | Use For |
+|------|-------|---------|
+| `frontend` | .rdc/guides/frontend.md | React, pages, UI, Tailwind |
+| `backend` | .rdc/guides/backend.md | API routes, database, auth |
+| `data` | .rdc/guides/data.md | Migrations, schema, RPC |
+| `design` | .rdc/guides/design.md | Brand, palette, OG images |
+| `infra` | .rdc/guides/infrastructure.md | CI/CD, deploy, DNS |
+| `content` | .rdc/guides/content.md | Copy, messaging, tone |
+| `cs2` | .rdc/guides/cs2.md | CS 2.0 paradigm |
+| `hail` | .rdc/guides/cs2.md + packages/hail/CLAUDE.md | Grammar, DSL |
+| `viz` | .rdc/guides/frontend.md + design.md | Custom visualizations |
+
+## What NOT to Do
+
+- Never raw INSERT/UPDATE against work items — RPC functions only
+- Never create tasks without a parent epic
+- Never leave labels empty
+- Never write vague titles ("Fix stuff") — be specific
+- Never put design intention in the task — put it in `.rdc/research/` (fallback: `.rdc/research/`) and link

package/tests/acceptance.test.mjs

@@ -1,59 +1,59 @@
-#!/usr/bin/env node
-import assert from 'node:assert/strict';
-import { spawnSync } from 'node:child_process';
-import { mkdtempSync, rmSync } from 'node:fs';
-import { tmpdir } from 'node:os';
-import { join, resolve } from 'node:path';
-import { fileURLToPath } from 'node:url';
-import { dirname } from 'node:path';
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-const REPO_ROOT = resolve(__dirname, '..');
-const script = join(REPO_ROOT, 'scripts', 'acceptance.mjs');
-const { codexToolCalls, normalizeSkillName } = await import(`file://${script.replace(/\\/g, '/')}`);
-
-const syntax = spawnSync(process.execPath, ['--check', script], { encoding: 'utf8' });
-assert.equal(syntax.status, 0, syntax.stderr);
-
-const codexEvents = [
-  {
-    type: 'item.started',
-    item: {
-      type: 'command_execution',
-      command: 'pwsh -Command "rg -n regenerative C:/Dev/local-corpus"',
-    },
-  },
-].map((event) => JSON.stringify(event)).join('\n');
-const parsedCalls = codexToolCalls(codexEvents);
-assert.equal(parsedCalls[0]?.name, 'Grep');
-assert.match(parsedCalls[0]?.input?.command || '', /local-corpus/);
-assert.equal(normalizeSkillName('lifeai-brochure-author'), 'lifeai-brochure-author');
-assert.equal(normalizeSkillName('build'), 'rdc:build');
-
-const missing = spawnSync(process.execPath, [script, '--skill', 'rdc:not-a-real-skill'], {
-  cwd: REPO_ROOT,
-  encoding: 'utf8',
-});
-assert.equal(missing.status, 1);
-assert.match(missing.stderr, /missing acceptance manifest/);
-
-const codex = spawnSync(process.execPath, [script, '--engine', 'codex', '--skill', 'rdc:not-a-real-skill'], {
-  cwd: REPO_ROOT,
-  encoding: 'utf8',
-});
-assert.equal(codex.status, 1);
-assert.doesNotMatch(codex.stderr, /not wired/i);
-assert.match(codex.stderr, /missing acceptance manifest/);
-
-const emptyProject = mkdtempSync(join(tmpdir(), 'rdc-acceptance-empty-'));
-try {
-  const none = spawnSync(process.execPath, [script, '--changed', '--base', 'HEAD', '--project-root', emptyProject], {
-    cwd: REPO_ROOT,
-    encoding: 'utf8',
-  });
-  assert.notEqual(none.status, 0);
-} finally {
-  rmSync(emptyProject, { recursive: true, force: true });
-}
-
-console.log('acceptance tests — PASS');
+#!/usr/bin/env node
+import assert from 'node:assert/strict';
+import { spawnSync } from 'node:child_process';
+import { mkdtempSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { dirname } from 'node:path';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const REPO_ROOT = resolve(__dirname, '..');
+const script = join(REPO_ROOT, 'scripts', 'acceptance.mjs');
+const { codexToolCalls, normalizeSkillName } = await import(`file://${script.replace(/\\/g, '/')}`);
+
+const syntax = spawnSync(process.execPath, ['--check', script], { encoding: 'utf8' });
+assert.equal(syntax.status, 0, syntax.stderr);
+
+const codexEvents = [
+  {
+    type: 'item.started',
+    item: {
+      type: 'command_execution',
+      command: 'pwsh -Command "rg -n regenerative C:/Dev/local-corpus"',
+    },
+  },
+].map((event) => JSON.stringify(event)).join('\n');
+const parsedCalls = codexToolCalls(codexEvents);
+assert.equal(parsedCalls[0]?.name, 'Grep');
+assert.match(parsedCalls[0]?.input?.command || '', /local-corpus/);
+assert.equal(normalizeSkillName('lifeai-brochure-author'), 'lifeai-brochure-author');
+assert.equal(normalizeSkillName('build'), 'rdc:build');
+
+const missing = spawnSync(process.execPath, [script, '--skill', 'rdc:not-a-real-skill'], {
+  cwd: REPO_ROOT,
+  encoding: 'utf8',
+});
+assert.equal(missing.status, 1);
+assert.match(missing.stderr, /missing acceptance manifest/);
+
+const codex = spawnSync(process.execPath, [script, '--engine', 'codex', '--skill', 'rdc:not-a-real-skill'], {
+  cwd: REPO_ROOT,
+  encoding: 'utf8',
+});
+assert.equal(codex.status, 1);
+assert.doesNotMatch(codex.stderr, /not wired/i);
+assert.match(codex.stderr, /missing acceptance manifest/);
+
+const emptyProject = mkdtempSync(join(tmpdir(), 'rdc-acceptance-empty-'));
+try {
+  const none = spawnSync(process.execPath, [script, '--changed', '--base', 'HEAD', '--project-root', emptyProject], {
+    cwd: REPO_ROOT,
+    encoding: 'utf8',
+  });
+  assert.notEqual(none.status, 0);
+} finally {
+  rmSync(emptyProject, { recursive: true, force: true });
+}
+
+console.log('acceptance tests — PASS');