session-orchestrator 3.24.0 → 4.0.1

package/.agents/skills/repo-audit/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: repo-audit
+description: "Use this skill when the user wants to audit a repository for baseline compliance, check code quality, security posture, CI/CD setup, testing, documentation, and ecosystem configuration. Runs 9 checklist categories and emits a Markdown report plus JSON sidecar at .orchestrator/metrics/repo-audit-<timestamp>.json. <example>Context: User is in a project repo and wants a baseline compliance check. user: \"/repo-audit\" assistant: \"Running repo-audit across 9 categories — Configuration, Code Quality, Git Hygiene, CI/CD, Testing, Security, Documentation, Clank Integration (optional), and MCP Configuration. Will produce a Markdown checklist report and JSON sidecar.\" <commentary>The user wants a compliance check; this skill is appropriate because it runs all 9 categories with pass/fail/warn/skipped statuses and writes structured output.</commentary></example>"
+metadata:
+  model: inherit
+  color: cyan
+---
+
+# repo-audit
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/repo-audit/SKILL.md`](../../../skills/repo-audit/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/session-end/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: session-end
+description: "Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command."
+metadata:
+  user-invocable: "false"
+  tags: orchestration, verification, commits, issues
+  model: inherit
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
+---
+
+# session-end
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/session-end/SKILL.md`](../../../skills/session-end/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/session-plan/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: session-plan
+description: Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into configurable waves (default 5) with optimal agent assignment, dependency ordering, and inter-wave checkpoints. Activated by session-start after Q&A phase completes.
+metadata:
+  user-invocable: "false"
+  tags: orchestration, planning, waves, agents
+  model: inherit
+  model-preference: opus
+  model-preference-codex: gpt-5.4
+  model-preference-cursor: claude-opus-4-6
+---
+
+# session-plan
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/session-plan/SKILL.md`](../../../skills/session-plan/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/session-start/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: session-start
+description: Use this skill when initializing a session for any project repo. Autonomously analyzes git state, VCS issues, SSOT files, branches, environment, and cross-repo status. Then presents structured findings with recommendations for user alignment before creating a wave plan. Triggered by /session [housekeeping|feature|deep] command.
+metadata:
+  user-invocable: "false"
+  tags: orchestration, initialization, analysis, alignment
+  model: inherit
+  model-preference: opus
+  model-preference-codex: gpt-5.4
+  model-preference-cursor: claude-opus-4-6
+---
+
+# session-start
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/session-start/SKILL.md`](../../../skills/session-start/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/spinout/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: spinout
+description: "Use when extracting a project into its own repo — a venture spinout (e.g. a product leaving its incubator repo) or a sanitized content-snapshot fork. Guided 5-step runbook: target sphere + path, confidentiality/sanitize check, copy + fresh git init, SNAPSHOT-FREEZE marker in the source repo, remotes + registration. Trigger on 'spin out X', 'extract this into its own repo', 'fork X sanitized'."
+metadata:
+  user-invocable: "true"
+  model: sonnet
+---
+
+# spinout
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/spinout/SKILL.md`](../../../skills/spinout/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/sunset-review/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: sunset-review
+description: "Use this skill when the user wants to identify unused, near-zero-use, or stale skills/agents/commands in the plugin surface so they can be demoted or retired. Combines agent-dispatch telemetry (start-events only) with static reference scanning, classifies every surface item into Active / Investigate / Demote / Retire, and emits a Markdown report plus JSON sidecar. NEVER auto-deletes — surfaces candidates for human decision. Quarterly cadence. <example>Context: The plugin surface has grown and the maintainer wants to prune dead weight. user: \"/sunset-review\" assistant: \"Running the sunset walk — classifying skills, agents, and commands by usage telemetry + static refs, grouped by Retire / Demote / Investigate / Active. No item is deleted automatically; I'll surface Retire/Demote candidates for your decision.\" <commentary>The user wants a usage-driven prune candidate list; this skill runs the read-only walker, presents grouped verdicts, and writes a sidecar — it never deletes.</commentary></example>"
+metadata:
+  model: inherit
+  color: amber
+---
+
+# sunset-review
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/sunset-review/SKILL.md`](../../../skills/sunset-review/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/test-runner/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: test-runner
+description: "Use this skill when orchestrating agentic end-to-end tests. Resolves target + profile, dispatches the right driver(s) (playwright for web today, peekaboo for macOS (issue #381)), invokes the ux-evaluator agent (opus, read-only) against driver artifacts, reconciles findings with the open issue tracker via scripts/lib/test-runner/issue-reconcile.mjs, and writes report.md + JSONL roll-up. Wraps upstream tools (no forks). Hard-gates Playwright MCP for browser drive (4× token cost vs CLI per Microsoft's own benchmark)."
+metadata:
+  user-invocable: "false"
+  tags: test, orchestrator, e2e, ux
+  model: sonnet
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4
+  model-preference-cursor: claude-sonnet-4-6
+---
+
+# test-runner
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/test-runner/SKILL.md`](../../../skills/test-runner/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/tmux-layout/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: tmux-layout
+description: "Use this skill when the operator wants a prepared tmux visualization layout for the session's side-channels (STATE.md tail, CI-watch, events.jsonl tail). Renders a 4-pane default layout or debug layout. Read-only side-channel observability — the coordinator chat stays in the operator's original terminal. Trigger phrases: \"tmux layout\", \"split panes for ci watch\", \"visualize session side-channels\", \"show me state-md tail and ci\"."
+metadata:
+  model: inherit
+  color: cyan
+allowed-tools:
+  - Read
+  - Bash
+  - Grep
+  - Glob
+---
+
+# tmux-layout
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/tmux-layout/SKILL.md`](../../../skills/tmux-layout/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/using-orchestrator/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: using-orchestrator
+description: "Use this skill when dispatching implicit slash-command intent from the user's first message. Inspects the user's first message for implicit slash-command intent and dispatches to the highest-confidence matching entry-point skill via the Skill tool. Only active when `auto-skill-dispatch: true` in Session Config. Silent no-op otherwise."
+metadata:
+  user-invocable: "false"
+  tags: dispatch, meta, routing, auto-skill
+  model: haiku
+---
+
+# using-orchestrator
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/using-orchestrator/SKILL.md`](../../../skills/using-orchestrator/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/vault-mirror/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: vault-mirror
+description: "Use when you need to populate the Meta-Vault with machine-generated notes derived from session-orchestrator JSONL records. Converts entries from `.orchestrator/metrics/sessions.jsonl` and `.orchestrator/metrics/learnings.jsonl` into vault-conformant Markdown under `50-sessions/` and `40-learnings/`. Called automatically at session-end Phase 3.7 and after evolve Phase 3.5 — only when `vault-integration.enabled=true` and `vault-integration.mode != \"off\"`. Idempotent: re-runs safely; skips hand-authored notes. Triggers: \"mirror to vault\", \"sync session notes to vault\", \"write learning notes to vault\", \"vault-mirror failed at session close\". <example>Context: session-end is finalizing, vault-integration.mode is \"warn\". user: \"/close\" assistant: \"Running vault-mirror to write 50-sessions/session-2026-05-17.md from the closing session record — 1 created, 0 skipped.\"</example>"
+metadata:
+  model: haiku
+---
+
+# vault-mirror
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/vault-mirror/SKILL.md`](../../../skills/vault-mirror/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/vault-sync/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: vault-sync
+description: "Use when you need to validate the Meta-Vault's Markdown frontmatter and wiki-link integrity before closing a session or after vault edits. Runs as a hard gate at session-end Phase 1 — blocks close if any `.md` file fails the Zod frontmatter schema or has dangling `[[wiki-links]]`. Supports three modes: `hard` (blocks on errors), `warn` (reports without blocking), `off` (skip). Reads `vault-sync.*` from Session Config; respects per-vault exclude globs from `CLAUDE.md`. Triggers: \"vault validation failed at session close\", \"fix vault frontmatter errors\", \"check vault wiki-links\", \"why is session-end blocked by vault-sync\". <example>Context: session-end Phase 1 quality gate, vault-sync.enabled=true, vault-sync.mode=\"hard\". user: \"/close\" assistant: \"vault-sync found 2 frontmatter errors in vault/40-learnings/ml-notes.md — missing required `id` field. Fixing before close.\"</example>"
+metadata:
+  model: haiku
+---
+
+# vault-sync
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/vault-sync/SKILL.md`](../../../skills/vault-sync/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/wave-executor/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: wave-executor
+description: Use this skill when executing the agreed session plan in waves with role-based execution and parallel subagents. Handles inter-wave quality checks, plan adaptation, and progress tracking. Core orchestration engine for feature and deep sessions. Triggered by /go command.
+metadata:
+  user-invocable: "false"
+  tags: orchestration, execution, agents, waves
+  model: inherit
+  model-preference: opus
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
+---
+
+# wave-executor
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/wave-executor/SKILL.md`](../../../skills/wave-executor/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.agents/skills/write-executable-plan/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: write-executable-plan
+description: Use when you have a PRD or design spec and need a bite-sized, executable implementation plan that any agent can follow without re-deriving structure. Produces `docs/plans/YYYY-MM-DD-<feature>.md` with per-task Files block, complete code per step (no placeholders), and exact verification commands. Rejects "TBD", "TODO", "add error handling", "similar to Task N".
+metadata:
+  model: inherit
+  color: green
+allowed-tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
+---
+
+# write-executable-plan
+
+> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> [`skills/write-executable-plan/SKILL.md`](../../../skills/write-executable-plan/SKILL.md); read that file for the full instructions.
+> This mirror carries only agentskills.io-spec-legal frontmatter so harnesses that
+> discover skills under `.agents/skills/` can find and route to the skill.
+>
+> Regenerate with `node scripts/generate-agents-skills.mjs`.

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
   },
   "metadata": {
     "description": "Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.",
-    "version": "3.24.0"
+    "version": "4.0.1"
   },
   "plugins": [
     {

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "session-orchestrator",
-  "version": "3.24.0",
+  "version": "4.0.1",
   "description": "Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.",
   "author": {
     "name": "Bernhard Goetzendorfer",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "session-orchestrator",
-  "version": "3.24.0+codex.20260902192928",
+  "version": "4.0.1+codex.20260907191442",
   "description": "Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.",
   "keywords": [
     "session",
@@ -11,7 +11,8 @@
     "quality-gates",
     "codex"
   ],
-  "skills": "./skills/",
+  "skills": "./.codex-plugin/skills/",
+  "commands": [],
   "hooks": "./hooks/hooks-codex.json",
   "mcpServers": "./.mcp.json",
   "interface": {

package/.codex-plugin/skills/architecture/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: architecture
+description: Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable. Surfaces shallow modules and hypothetical seams using a precise vocabulary (Module / Interface / Implementation / Depth / Seam / Adapter / Leverage / Locality from LANGUAGE.md).
+license: MIT
+metadata:
+  model: inherit
+  derived-from: mattpocock/skills@90ea8ee
+  upstream-url: https://github.com/mattpocock/skills/tree/main/improve-codebase-architecture
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# architecture
+
+Read [`skills/architecture/SKILL.md`](../../../skills/architecture/SKILL.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/autopilot/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: autopilot
+description: Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped)
+metadata:
+  argument-hint: '[--headless] [--verbose] [--max-sessions=N] [--max-hours=H] [--confidence-threshold=0.X] [--dry-run]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# autopilot
+
+Read [`commands/autopilot.md`](../../../commands/autopilot.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/autopilot/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: autopilot
+policy:
+  allow_implicit_invocation: true

package/.codex-plugin/skills/bootstrap/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: bootstrap
+description: Scaffold the minimum repo structure required by session-orchestrator
+metadata:
+  disable-model-invocation: 'true'
+  argument-hint: '[--upgrade <tier>]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# bootstrap
+
+Read [`commands/bootstrap.md`](../../../commands/bootstrap.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/bootstrap/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: bootstrap
+policy:
+  allow_implicit_invocation: false

package/.codex-plugin/skills/brainstorm/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: brainstorm
+description: Run a lightweight Socratic design dialogue (3-5 AUQ rounds) and write a spec markdown file before any implementation work. Use BEFORE /plan feature when scope/UX is ambiguous.
+metadata:
+  disable-model-invocation: 'true'
+  argument-hint: '[topic-or-feature-slug]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# brainstorm
+
+Read [`commands/brainstorm.md`](../../../commands/brainstorm.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/brainstorm/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: brainstorm
+policy:
+  allow_implicit_invocation: false

package/.codex-plugin/skills/claude-md-drift-check/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: claude-md-drift-check
+description: 'Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Ten checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness, session-file existence, command-count sync, session-config-parity (mandatory template keys = error, opt-in gaps = warning), vault-dir-parity (CLAUDE.md vs AGENTS.md), generated-rule-staleness (WARN-only), rule-scoping (paths:/globs: frontmatter defects, dangling rule citations, zero-match globs), and docs-parity (docs/components.md count-claims vs on-disk counts, template-vs-reference config-key parity, stale .claude/metrics/ paths). Full per-check spec in the body table. Invoked as an opt-in session-end phase; mirrors vault-sync''s lean JSON+exit-code contract.'
+metadata:
+  model: haiku
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# claude-md-drift-check
+
+Read [`skills/claude-md-drift-check/SKILL.md`](../../../skills/claude-md-drift-check/SKILL.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/close/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: close
+description: End session with verification, commits, and documentation
+metadata:
+  disable-model-invocation: 'true'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# close
+
+Read [`commands/close.md`](../../../commands/close.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/close/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: close
+policy:
+  allow_implicit_invocation: false

package/.codex-plugin/skills/convergence-monitoring/SKILL.md

@@ -0,0 +1,24 @@
+---
+name: convergence-monitoring
+description: 'Monitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive a Stop/Continue/Investigate decision at each inter-wave checkpoint. Distinct from /evolve (retrospective) and session-reviewer (wave output review): convergence-monitoring answers "are we making progress?" not "was the last wave correct?". Primary consumer: /autoresearch loops and wave-executor inter-wave checkpoints.'
+metadata:
+  user-invocable: 'true'
+  tags: autoresearch, convergence, loop-control, wave-executor
+  model: haiku
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
+  attribution: |
+    Inspired by cavekit's documented convergence-monitoring concept (MIT, Julius Brussee). Implemented from spec since upstream skill not yet published as of 2026-04-30.
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# convergence-monitoring
+
+Read [`skills/convergence-monitoring/SKILL.md`](../../../skills/convergence-monitoring/SKILL.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/debug/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: debug
+description: Run a 4-phase systematic debugging investigation before proposing any fix. Iron Law — NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a `.orchestrator/debug/` artifact the fixer agent must reference.
+metadata:
+  argument-hint: '[bug-description-or-issue-ref]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# debug
+
+Read [`commands/debug.md`](../../../commands/debug.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/debug/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: debug
+policy:
+  allow_implicit_invocation: true

package/.codex-plugin/skills/discovery/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: discovery
+description: Systematic quality discovery and issue detection
+metadata:
+  argument-hint: '[all|code|infra|ui|arch|session|audit|vault|feature] [--since <git-ref>] [--full]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# discovery
+
+Read [`commands/discovery.md`](../../../commands/discovery.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/discovery/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: discovery
+policy:
+  allow_implicit_invocation: true

package/.codex-plugin/skills/dispatcher/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: dispatcher
+description: Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command
+metadata:
+  argument-hint: '[--dry-run] [--repo <name>]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# dispatcher
+
+Read [`commands/dispatcher.md`](../../../commands/dispatcher.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+`$ARGUMENTS` means the trailing user input after the selected command skill, or an empty string when absent. Preserve flags, quoted text, and Unicode as data. Do not perform global substitution in the command document, shell expansion on the argument string, or execution of that string as shell code. When the workflow needs a command, pass its arguments through structured tool parameters or safely quoted individual arguments.
+
+Read the full command before invoking an internal skill. An instruction to invoke a skill (including `session-orchestrator:<name>` or the `Skill` tool) means read and follow the canonical `skills/<name>/SKILL.md` beneath the plugin root. Do not redispatch the public command adapter: a same-named command and internal skill are distinct documents, and redispatch would recurse.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

package/.codex-plugin/skills/dispatcher/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: dispatcher
+policy:
+  allow_implicit_invocation: true

package/.codex-plugin/skills/docs-orchestrator/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: docs-orchestrator
+description: 'Use this skill when orchestrating documentation generation and updates within a session. Maps session scope to audience-specific docs tasks (User / Dev / Vault), dispatches the docs-writer agent with source-grounded prompts, and reports coverage gaps to session-end. Gated on `docs-orchestrator.enabled: true` in Session Config. Zero overhead when disabled.'
+metadata:
+  user-invocable: 'false'
+  tags: docs, orchestration, audiences
+  model: sonnet
+  model-preference: sonnet
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# docs-orchestrator
+
+Read [`skills/docs-orchestrator/SKILL.md`](../../../skills/docs-orchestrator/SKILL.md) in full before taking any action, then follow its complete workflow.
+The linked document is authoritative, including its prechecks, argument rules, and stop conditions.
+
+Resolve this link relative to this SKILL.md, not the project working directory. The plugin root is three directories above this file. Resolve package paths such as `skills/` and `scripts/` from that root; resolve relative links inside the canonical document from its own directory. Keep the user’s project as the target of project operations.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.