session-orchestrator 5.1.0 → 5.3.0

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

@@ -14,9 +14,11 @@ allowed-tools:
 
 # write-executable-plan
 
-> **Portable mirror — generated, do not edit.** The canonical skill body lives at
+> **Portable mirror — generated, do not edit.** The canonical workflow 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`.
+
+Read the linked document in full and follow its complete workflow, including prechecks and stop conditions. Resolve its 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 and relative links in the canonical document from its own directory. Keep the user’s project as the target of project operations.

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
   },
   "metadata": {
     "description": "A repeatable Plan, Go, Close workflow for AI coding sessions: /session reads your repo and agrees the scope, /go runs the work in waves with a quality gate between each, /close verifies and commits. Runs on Claude Code, Codex CLI, Cursor and Pi.",
-    "version": "5.1.0"
+    "version": "5.3.0"
   },
   "plugins": [
     {

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "session-orchestrator",
-  "version": "5.1.0",
+  "version": "5.3.0",
   "description": "A repeatable Plan, Go, Close workflow for AI coding sessions: /session reads your repo and agrees the scope, /go runs the work in waves with a quality gate between each, /close verifies and commits. 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": "5.1.0+codex.20260913171452",
+  "version": "5.3.0+codex.20260922063114",
   "description": "A repeatable Plan, Go, Close workflow for AI coding sessions: /session reads your repo and agrees the scope, /go runs the work in waves with a quality gate between each, /close verifies and commits. Runs on Claude Code, Codex CLI, Cursor and Pi.",
   "keywords": [
     "session",
@@ -30,9 +30,9 @@
     "privacyPolicyURL": "https://gotzendorfer.at/en/session-orchestrator/privacy",
     "termsOfServiceURL": "https://gotzendorfer.at/en/session-orchestrator/terms",
     "defaultPrompt": [
-      "Start a structured feature session for this repo",
-      "Plan a feature PRD and turn it into waves",
-      "Close the current session with verification"
+      "$session-orchestrator:session",
+      "$session-orchestrator:go",
+      "$session-orchestrator:close"
     ]
   }
 }

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

@@ -1,21 +1,22 @@
 ---
 name: autopilot
-description: Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped)
+description: 'Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with all 10 kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, max-sessions, resource-overload, token-budget, stall-timeout, sub-threshold confidence, user-abort). Reads Mode-Selector output (Phase B) to decide auto-execute vs. fallback. Writes one autopilot.jsonl record per loop run. Phase C scaffold (issue #277); implementation lives in scripts/lib/autopilot.mjs (Phase C-1 follow-up).'
 metadata:
+  user-invocable: 'true'
   argument-hint: '[--headless] [--verbose] [--max-sessions=N] [--max-hours=H] [--confidence-threshold=0.X] [--dry-run]'
+  tags: phase-c, autopilot, autonomous, loop
+  model: sonnet
 ---
 
 <!-- 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.
+Read [`skills/autopilot/SKILL.md`](../../../skills/autopilot/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.
 
 `$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/SKILL.md

@@ -1,22 +1,26 @@
 ---
 name: bootstrap
-description: Scaffold the minimum repo structure required by session-orchestrator
+description: 'Use this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked automatically by the Bootstrap Gate when CLAUDE.md, Session Config, or bootstrap.lock is missing. Also available as /bootstrap for manual invocation. Three intensity tiers: fast (demos/spikes), standard (MVPs), deep (production/team).'
 metadata:
+  user-invocable: 'true'
   disable-model-invocation: 'true'
   argument-hint: '[--upgrade <tier>]'
+  tags: bootstrap, setup, scaffold, init
+  model: sonnet
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
 ---
 
 <!-- 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.
+Read [`skills/bootstrap/SKILL.md`](../../../skills/bootstrap/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.
 
 `$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/SKILL.md

@@ -1,22 +1,29 @@
 ---
 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.
+description: Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue (3-5 AUQ rounds) and writes a spec markdown file. Use BEFORE /plan feature when product intent needs validation; skip to /plan feature when scope is already clear. HARD-GATE prevents any code work until the design is user-approved.
 metadata:
+  model: inherit
+  color: cyan
+  user-invocable: 'true'
   disable-model-invocation: 'true'
   argument-hint: '[topic-or-feature-slug]'
+allowed-tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
 ---
 
 <!-- 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.
+Read [`skills/brainstorm/SKILL.md`](../../../skills/brainstorm/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.
 
 `$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/SKILL.md

@@ -2,20 +2,20 @@
 name: close
 description: End session with verification, commits, and documentation
 metadata:
+  user-invocable: 'true'
   disable-model-invocation: 'true'
+  model: inherit
 ---
 
 <!-- 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.
+Read [`skills/close/SKILL.md`](../../../skills/close/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.
 
 `$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/convergence-monitoring/SKILL.md

@@ -2,7 +2,7 @@
 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'
+  user-invocable: 'false'
   tags: autoresearch, convergence, loop-control, wave-executor
   model: haiku
   model-preference: sonnet

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

@@ -1,21 +1,28 @@
 ---
 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.
+description: 'Use when encountering any bug, test failure, build break, or unexpected behavior — runs a 4-phase systematic debugging process before proposing any fix. Iron Law: NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a `.orchestrator/debug/` artifact the fixer agent must reference.'
 metadata:
+  model: inherit
+  color: red
+  user-invocable: 'true'
   argument-hint: '[bug-description-or-issue-ref]'
+allowed-tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
 ---
 
 <!-- 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.
+Read [`skills/debug/SKILL.md`](../../../skills/debug/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.
 
 `$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/SKILL.md

@@ -1,21 +1,25 @@
 ---
 name: discovery
-description: Systematic quality discovery and issue detection
+description: Use this skill when running systematic quality discovery and issue detection. Runs modular probes adapted to the project's tech stack, presents findings interactively for user triage, and creates VCS issues for confirmed problems. Invoked standalone via /discovery or embedded in session-end.
 metadata:
+  user-invocable: 'true'
   argument-hint: '[all|code|infra|ui|arch|session|audit|vault|feature] [--since <git-ref>] [--full]'
+  tags: quality, discovery, probes, issues
+  model: sonnet
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
 ---
 
 <!-- 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.
+Read [`skills/discovery/SKILL.md`](../../../skills/discovery/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.
 
 `$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/SKILL.md

@@ -1,21 +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
+description: 'Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo''s session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one via AskUserQuestion, atomically claims it, and routes you to the chosen entry command. Triggers: "what should I work on next", "dispatch me to a repo", "pick the next project", "run /dispatcher". <example>Context: operator finished a session and wants the next-best repo across the portfolio. user: "/dispatcher" assistant: "Ranked 18 free repos — top recommendation: Pencil-Designs (score 4.50, 90d stale). Confirm via the picker, I''ll claim its lease atomically, then route you to /session deep."</example>'
 metadata:
+  user-invocable: 'true'
   argument-hint: '[--dry-run] [--repo <name>]'
+  model: sonnet
 ---
 
 <!-- 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.
+Read [`skills/dispatcher/SKILL.md`](../../../skills/dispatcher/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.
 
 `$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/eli5/SKILL.md

@@ -1,21 +1,26 @@
 ---
 name: eli5
-description: Say the last answer again in plain words — same facts, in the order the operator needs them. Optional topic argument.
+description: Explain a topic like I'm a 5 year old — restate my last output, or a named topic, in plain words without dropping a single fact. Use when the user types /eli5 [topic], or says an answer was too technical, too long, or unclear about what he now has to do.
 metadata:
+  user-invocable: 'true'
   argument-hint: '[topic]'
+  model: inherit
+allowed-tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # eli5
 
-Read [`commands/eli5.md`](../../../commands/eli5.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/eli5/SKILL.md`](../../../skills/eli5/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.
 
 `$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/eval/SKILL.md

@@ -1,21 +1,26 @@
 ---
 name: eval
-description: Run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed session against the pre-registered rubric-v1 dimensions
+description: Use this skill to run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed orchestrator session against the pre-registered rubric-v2 dimensions, run /eval, evaluate this session, produce an eval report, or re-verify a stored eval run for reproducibility. Deterministic-first with an optional advisory LLM judge; never produces a global score.
 metadata:
+  user-invocable: 'true'
   argument-hint: '[--session <id>] [--no-write] [--verify <run-id>]'
+  tags: eval, measurement, quality, meta, standard
+  model: sonnet
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
+  args-schema: '[{"flag":"--session","description":"session_id to evaluate (default: last completed session via the resolution cascade)"},{"flag":"--no-write","description":"Evaluate + report without appending to the eval journal (.orchestrator/metrics/eval.jsonl)"},{"flag":"--verify","description":"Re-evaluate a stored run-id and diff per-dimension for scoring drift (exit 1 on drift)"}]'
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # eval
 
-Read [`commands/eval.md`](../../../commands/eval.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/eval/SKILL.md`](../../../skills/eval/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.
 
 `$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/evolve/SKILL.md

@@ -1,21 +1,26 @@
 ---
 name: evolve
-description: Extract session patterns into reusable learnings
+description: 'Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.'
 metadata:
+  user-invocable: 'true'
   argument-hint: '[analyze|review|list|dialectic [--apply]]'
+  tags: learning, intelligence, meta
+  model: sonnet
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
+  args-schema: '[{"flag":"--apply","description":"Apply dialectic-derived diff to USER.md + AGENT.md"},{"flag":"--dry-run","description":"Show diff without writing (default)"},{"flag":"--model <name>","description":"Override single-pass LLM (haiku|sonnet|opus)"},{"flag":"--budget-tokens <N>","description":"Input token ceiling for derivation prompt (default 32000; aborts above it, never truncates)"}]'
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # evolve
 
-Read [`commands/evolve.md`](../../../commands/evolve.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/evolve/SKILL.md`](../../../skills/evolve/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.
 
 `$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/go/SKILL.md

@@ -2,21 +2,21 @@
 name: go
 description: Approve session plan and begin wave execution
 metadata:
+  user-invocable: 'true'
   disable-model-invocation: 'true'
   argument-hint: '[optional instructions]'
+  model: inherit
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # go
 
-Read [`commands/go.md`](../../../commands/go.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/go/SKILL.md`](../../../skills/go/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.
 
 `$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/grill/SKILL.md

@@ -1,21 +1,28 @@
 ---
 name: grill
-description: Stress-test a plan, design, or PRD before any build — relentless one-question-at-a-time interrogation that hunts contradictions against the code and challenges assumptions. Composable; no HARD-GATE.
+description: Use when the user wants a plan, design, or PRD stress-tested before any build — relentlessly interrogates one decision at a time, grounds every question in the codebase, hunts contradictions against the domain language and the code, and challenges the load-bearing assumptions. Triggered by "grill me", "stress-test this plan", "poke holes in my design". Composable — run standalone or as an adversarial pass before /plan feature.
 metadata:
+  user-invocable: 'true'
   argument-hint: '[file-path-or-topic]'
+  model: inherit
+  color: red
+allowed-tools:
+  - Read
+  - Grep
+  - Glob
+  - Bash
+  - Write
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # grill
 
-Read [`commands/grill.md`](../../../commands/grill.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/grill/SKILL.md`](../../../skills/grill/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.
 
 `$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/harness-audit/SKILL.md

@@ -1,19 +1,20 @@
 ---
 name: harness-audit
 description: Run the harness audit and report the rubric score for this repository
+metadata:
+  user-invocable: 'true'
+  model: inherit
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # harness-audit
 
-Read [`commands/harness-audit.md`](../../../commands/harness-audit.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/harness-audit/SKILL.md`](../../../skills/harness-audit/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.
 
 `$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/memory-cleanup/SKILL.md

@@ -1,21 +1,26 @@
 ---
 name: memory-cleanup
-description: Manual memory consolidation — review, consolidate, and prune memory files (Dream-equivalent)
+description: Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under ~/.claude/projects/*/memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke with /memory-cleanup.
 metadata:
+  user-invocable: 'true'
   argument-hint: '[--dry-run | --apply-pending]'
+  tags: memory, maintenance, meta, dream
+  model: sonnet
+  model-preference: sonnet
+  model-preference-codex: gpt-5.4-mini
+  model-preference-cursor: claude-sonnet-4-6
+  args-schema: '[{"flag":"--dry-run","description":"Produce complete-body proposal in .orchestrator/pending-dream.md, no mutations."},{"flag":"--apply-pending","description":"Consume .orchestrator/pending-dream.md (atomic apply)."}]'
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # memory-cleanup
 
-Read [`commands/memory-cleanup.md`](../../../commands/memory-cleanup.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/memory-cleanup/SKILL.md`](../../../skills/memory-cleanup/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.
 
 `$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/npm-publish/SKILL.md

@@ -2,7 +2,7 @@
 name: npm-publish
 description: Use when publishing this package to npm — a version release (npm publish), verifying the registry/pi.dev listing, or diagnosing npm auth failures (E403 2FA/token errors). Token-based flow via NPM_TOKEN in .env.local with a temp userconfig, the leakage gate before every publish, post-publish verification and marker/badge upkeep. Trigger on "publish to npm", "npm release", "E403 publish error".
 metadata:
-  user-invocable: 'true'
+  user-invocable: 'false'
   model: sonnet
 ---
 

package/.codex-plugin/skills/persona-panel/SKILL.md

@@ -1,22 +1,22 @@
 ---
 name: persona-panel
-description: Run a parallel multi-persona domain-expert review panel against a file, directory, or output range
+description: Use this skill when you need multi-persona parallel content review — domain experts, buyer personas, compliance reviewers, or custom catalog entries reviewing a target file or output. Dispatches N persona agents in parallel, consolidates verdicts via a configurable mode (voting-quorum, hard-gate-threshold, or coordinator-summary), and writes a timestamped sidecar to .orchestrator/persona-panel/. Invoked via /persona-panel <target-path>.
 metadata:
+  user-invocable: 'true'
   argument-hint: <target> [--personas <names,...>] [--mode <voting|hard-gate|summary>] [--threshold <M-of-N|all|any>] [--grounding <off|re-derive>] [--dry-run]
-  disable-model-invocation: 'false'
+  tags: review, personas, content, quality, multi-agent
+  model: inherit
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # persona-panel
 
-Read [`commands/persona-panel.md`](../../../commands/persona-panel.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/persona-panel/SKILL.md`](../../../skills/persona-panel/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.
 
 `$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/plan/SKILL.md

@@ -1,22 +1,26 @@
 ---
 name: plan
-description: Plan a new project, feature, or retrospective with structured requirement gathering
+description: 'Use this skill when performing structured project planning and PRD generation with three modes: new (project kickoff with repo scaffolding), feature (compact feature PRD), retro (data-driven retrospective). All modes share a researched Q&A engine that dispatches parallel Explore agents before each question wave, presents options via AskUserQuestion with recommendations, and produces documents with prioritized issue creation.'
 metadata:
+  user-invocable: 'true'
   disable-model-invocation: 'true'
   argument-hint: '[new|feature|retro]'
+  tags: planning, prd, requirements, research
+  model: inherit
+  model-preference: opus
+  model-preference-codex: gpt-5.4
+  model-preference-cursor: claude-opus-4-6
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # plan
 
-Read [`commands/plan.md`](../../../commands/plan.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/plan/SKILL.md`](../../../skills/plan/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.
 
 `$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/portfolio/SKILL.md

@@ -2,20 +2,20 @@
 name: portfolio
 description: Aggregate cross-repo issue/MR/CI health across vault-registered projects into a single Markdown dashboard
 metadata:
+  user-invocable: 'true'
   argument-hint: '[--dry-run] [--repo <name>]'
+  model: inherit
 ---
 
 <!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
 
 # portfolio
 
-Read [`commands/portfolio.md`](../../../commands/portfolio.md) in full before taking any action, then follow its complete workflow.
+Read [`skills/portfolio/SKILL.md`](../../../skills/portfolio/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.
 
 `$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`.