session-orchestrator 3.24.0 → 4.0.1

package/.codex-plugin/skills/ecosystem-health/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: ecosystem-health
+description: Monitor health across configured service endpoints, CI pipelines, and critical issues. Automatically invoked during session-start when ecosystem-health is enabled in Session Config.
+metadata:
+  user-invocable: 'false'
+  tags: reference, health, monitoring, ci, endpoints
+  model: haiku
+  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. -->
+
+# ecosystem-health
+
+Read [`skills/ecosystem-health/SKILL.md`](../../../skills/ecosystem-health/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/eli5/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: eli5
+description: Say the last answer again in plain words — same facts, in the order the operator needs them. Optional topic argument.
+metadata:
+  argument-hint: '[topic]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

@@ -0,0 +1,5 @@
+# Generated by scripts/generate-codex-skills.mjs; do not edit.
+interface:
+  display_name: eli5
+policy:
+  allow_implicit_invocation: true

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

@@ -0,0 +1,21 @@
+---
+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
+metadata:
+  argument-hint: '[--session <id>] [--no-write] [--verify <run-id>]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

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

@@ -0,0 +1,21 @@
+---
+name: evolve
+description: Extract session patterns into reusable learnings
+metadata:
+  argument-hint: '[analyze|review|list|dialectic [--apply]]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

package/.codex-plugin/skills/frontmatter-guard/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: frontmatter-guard
+description: 'Injects the canonical vault frontmatter schema snippet into agent prompts before any vault-write task, preventing malformed YAML frontmatter in Obsidian notes. <example>Context: wave-executor is about to dispatch a vault-mirror agent that writes learning notes under ~/Projects/vault/40-learnings/. user: "dispatch vault-write agent" assistant: "Injecting frontmatter-guard snippet into agent prompt (vault scope detected). Required fields: id, type, created, updated. Enum type: note|daily|project|person|reference|idea|learning|session." <commentary>The wave-executor pre-dispatch hook calls detectVaultTaskScope() — the fileScope contains /Projects/vault/40-learnings/ so the guard triggers and the snippet is prepended to the agent system prompt.</commentary></example>'
+metadata:
+  model: inherit
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# frontmatter-guard
+
+Read [`skills/frontmatter-guard/SKILL.md`](../../../skills/frontmatter-guard/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/gitlab-ops/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: gitlab-ops
+description: 'Use this skill when performing VCS operations on GitLab or GitHub repositories — creating, updating, or closing issues and MRs, applying label taxonomy, running `glab`/`gh` CLI commands, or resolving project paths dynamically. Acts as the single source of truth for CLI command syntax and label conventions; consuming skills reference this rather than duplicating logic. Triggers: "create a GitLab issue", "list open MRs", "apply priority label", "how do I resolve the project ID", "what''s the carryover issue template". <example>Context: session-end needs to file a carryover issue for an incomplete task. user: "/close" assistant: "Creating carryover issue via glab with the Carryover Template from gitlab-ops — labels: carryover, priority::high."</example>'
+metadata:
+  user-invocable: 'false'
+  tags: reference, vcs, gitlab, github, issues
+  model: haiku
+  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. -->
+
+# gitlab-ops
+
+Read [`skills/gitlab-ops/SKILL.md`](../../../skills/gitlab-ops/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/gitlab-portfolio/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: gitlab-portfolio
+description: 'Use when you need a single-pane cross-repo health view across all vault-registered GitLab and GitHub projects. Discovers repos from `_overview.md` frontmatter in `<vault>/01-projects/*/`, aggregates open issues, MRs, critical labels, and stale signals via parallel `glab`/`gh` calls, then writes an idempotent `_PORTFOLIO.md` dashboard. Runs automatically at session-start Phase 2 when `gitlab-portfolio.enabled=true`. Triggers: "show portfolio status", "refresh the portfolio dashboard", "which repos have critical issues", "run /portfolio". <example>Context: session-start, gitlab-portfolio.enabled=true, vault has 5 registered repos. user: "/session deep" assistant: "Portfolio: 3 critical issues across 2 repos — run /portfolio for details. Dashboard written to vault/01-projects/_PORTFOLIO.md."</example>'
+metadata:
+  model: sonnet
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# gitlab-portfolio
+
+Read [`skills/gitlab-portfolio/SKILL.md`](../../../skills/gitlab-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.
+
+Regenerate with `node scripts/generate-codex-skills.mjs`.

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

@@ -0,0 +1,22 @@
+---
+name: go
+description: Approve session plan and begin wave execution
+metadata:
+  disable-model-invocation: 'true'
+  argument-hint: '[optional instructions]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

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

@@ -0,0 +1,21 @@
+---
+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.
+metadata:
+  argument-hint: '[file-path-or-topic]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

package/.codex-plugin/skills/harness-audit/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: harness-audit
+description: Run the harness audit and report the rubric score for this repository
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

package/.codex-plugin/skills/hook-development/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: hook-development
+description: Use when creating, modifying, or debugging Claude Code hooks — PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification. Covers the plugin `hooks/hooks.json` wrapper format vs. the user `settings.json` direct format, matchers, security patterns, `$CLAUDE_PLUGIN_ROOT` portability, lifecycle limitations, and debugging. Trigger on "add a hook", "validate tool use", "block dangerous commands", "enforce completion", "hook-based automation".
+metadata:
+  model: sonnet
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# hook-development
+
+Read [`skills/hook-development/SKILL.md`](../../../skills/hook-development/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/mcp-builder/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: mcp-builder
+description: Use when creating a new MCP (Model Context Protocol) server, extending an existing one, or debugging tool discoverability/performance. Guides through research → implementation → test → eval phases with TypeScript-first guidance matching our stack. Trigger on phrases like "build an MCP server", "expose X as an MCP tool", "write MCP tools for Y", "integrate Z via MCP".
+metadata:
+  model: sonnet
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# mcp-builder
+
+Read [`skills/mcp-builder/SKILL.md`](../../../skills/mcp-builder/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/memory-cleanup/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: memory-cleanup
+description: Manual memory consolidation — review, consolidate, and prune memory files (Dream-equivalent)
+metadata:
+  argument-hint: '[--dry-run | --apply-pending]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

package/.codex-plugin/skills/mode-selector/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: mode-selector
+description: 'Use this skill when performing deterministic mode selection for session-start. Reads Phase A STATE.md recommendations + (future) learnings, sessions, backlog, bootstrap signals and returns {mode, rationale, confidence, alternatives}. Pure-function contract — no side effects, no STATE.md writes. Phase B scaffold (issue #276); full heuristic is follow-up sub-issues.'
+metadata:
+  model: haiku
+  user-invocable: 'false'
+  tags: phase-b, autopilot, mode-selection, scaffold
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# mode-selector
+
+Read [`skills/mode-selector/SKILL.md`](../../../skills/mode-selector/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/npm-publish/SKILL.md

@@ -0,0 +1,18 @@
+---
+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'
+  model: sonnet
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# npm-publish
+
+Read [`skills/npm-publish/SKILL.md`](../../../skills/npm-publish/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/peekaboo-driver/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: peekaboo-driver
+description: Use this skill when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by `skills/test-runner/` to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.
+metadata:
+  user-invocable: 'false'
+  tags: test, driver, macos, peekaboo
+  model: haiku
+  model-preference: sonnet
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# peekaboo-driver
+
+Read [`skills/peekaboo-driver/SKILL.md`](../../../skills/peekaboo-driver/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/persona-panel/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: persona-panel
+description: Run a parallel multi-persona domain-expert review panel against a file, directory, or output range
+metadata:
+  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'
+---
+
+<!-- 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.
+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/persona-panel/agents/openai.yaml

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

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

@@ -0,0 +1,22 @@
+---
+name: plan
+description: Plan a new project, feature, or retrospective with structured requirement gathering
+metadata:
+  disable-model-invocation: 'true'
+  argument-hint: '[new|feature|retro]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

package/.codex-plugin/skills/playwright-driver/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: playwright-driver
+description: Use this skill when executing web tests via the canonical `playwright` npm package (Microsoft, Apache-2.0). Dispatched by `skills/test-runner/` to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under `.orchestrator/metrics/test-runs/<run-id>/`, and exits with deterministic JSON output the orchestrator can parse.
+metadata:
+  user-invocable: 'false'
+  tags: test, driver, web, playwright
+  model: haiku
+  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. -->
+
+# playwright-driver
+
+Read [`skills/playwright-driver/SKILL.md`](../../../skills/playwright-driver/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/portfolio/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: portfolio
+description: Aggregate cross-repo issue/MR/CI health across vault-registered projects into a single Markdown dashboard
+metadata:
+  argument-hint: '[--dry-run] [--repo <name>]'
+---
+
+<!-- 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.
+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/agents/openai.yaml

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

package/.codex-plugin/skills/quality-gates/SKILL.md

@@ -0,0 +1,22 @@
+---
+name: quality-gates
+description: Use this skill when referencing canonical quality check commands for typecheck, test, and lint. Defines 4 variants (Baseline, Incremental, Full Gate, Per-File) used by session-start, wave-executor, session-end, and session-reviewer. Reference skill — not invoked directly.
+metadata:
+  user-invocable: 'false'
+  tags: reference, quality, typecheck, test, lint
+  model: haiku
+  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. -->
+
+# quality-gates
+
+Read [`skills/quality-gates/SKILL.md`](../../../skills/quality-gates/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/reconcile/SKILL.md

@@ -0,0 +1,21 @@
+---
+name: reconcile
+description: Reconcile learnings into .claude/rules/ proposals — on-demand version of session-end Phase 3.6.8
+metadata:
+  argument-hint: '[--dry-run]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# reconcile
+
+Read [`commands/reconcile.md`](../../../commands/reconcile.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/reconcile/agents/openai.yaml

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

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

@@ -0,0 +1,22 @@
+---
+name: release
+description: Cut a release — the order the steps must run in, and the criteria that abort a release
+metadata:
+  disable-model-invocation: 'true'
+  argument-hint: '[X.Y.Z]'
+---
+
+<!-- Generated by scripts/generate-codex-skills.mjs; do not edit. -->
+
+# release
+
+Read [`commands/release.md`](../../../commands/release.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/release/agents/openai.yaml

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