Skip to main content
title: AI Tools Governance Index sidebarTitle: AI Tools description: ‘Current governance entrypoint for the AI-tools registry, lane contract, audit-pipeline catalog, and generated pack outputs.’ keywords:
  • livepeer
  • ai tools
  • skills
  • audit
  • codex
  • cursor
  • claude
  • windsurf ‘og:image’: /snippets/assets/site/og-image/fallback.png ‘og:image:alt’: Livepeer Docs social preview image ‘og:image:type’: image/png ‘og:image:width’: 1200 ‘og:image:height’: 630

​
Wave 1 Canonical Registry

  • Canonical inventory + lifecycle + lane source: ai-tools/registry/ai-tools-registry.json
  • Registry schema: ai-tools/registry/ai-tools-registry.schema.json
  • Generated inventory report: ai-tools/registry/ai-tools-inventory.md
  • Validator CLI: tools/scripts/validate-ai-tools-registry.js
Primary commands: 
node tools/scripts/validate-ai-tools-registry.js --check --coverage
node tools/scripts/validate-ai-tools-registry.js --check --lanes
node tools/scripts/validate-ai-tools-registry.js --write-report
The registry is now the canonical source for what exists under ai-tools/**, how each artifact is classified, and which lane it belongs to.

​
Current Lane Model

LaneWhat it governs nowNotes
templatesai-tools/ai-skills/templates/**Canonical portable skill templates and companion bundles
localrepo-local SKILL.md roots under ai-tools/ai-skills/*/SKILL.mdIncludes both legacy local-only skills and template-synced local roots
workspaceresearch, packages, and source snapshots under ai-tools/ai-skills/Non-canonical material kept out of template/export lanes
exportsai-tools/agent-packs/**Generated agent-pack outputs and portable skill exports
rulesai-tools/ai-rules/**Legacy/internal rule surfaces pending later normalization
manual-docregistry, setup guides, pipeline catalog docs, and framework/support docsHuman-readable governance/support material
retiredreserved for future retired AI-tools materialNot active in Wave 1

​
Subsystem-Scoped Audit Pipeline Catalog

These files remain active and unchanged in role for the repo-audit pipeline, but they are not the full AI-tools registry:
  • Catalogue schema: ai-tools/ai-skills/catalog/skill-catalog.schema.json
  • Catalogue data: ai-tools/ai-skills/catalog/skill-catalog.json
  • Execution manifest: ai-tools/ai-skills/catalog/execution-manifest.json
Use these files only for:
  • repo-audit orchestrator run order and stage metadata
  • cross-agent packager manifest inputs
  • audit-pipeline policy docs that describe that subsystem specifically
The generated aggregate AI-tools catalog is deferred to Wave 2. Until then, use the registry and generated inventory report as the complete inventory surface.

​
Codex Planning Entry Point

  • Skill: agentic-project-management-orchestrator
  • Triggers: skill-plan, plan this repo change, full plan for this
  • Use this as the first step for ambiguous repo-change planning, especially when the work may touch docs content, navigation, scripts, generated indexes, or governance surfaces.

​
One-Command Audit

node tools/scripts/repo-audit-orchestrator.js --mode static --scope full

​
Cross-Agent Installation Path

Generate packs: 
node tools/scripts/cross-agent-packager.js --agent-pack all
Produced assets:
  • Codex: ai-tools/agent-packs/codex/skills-manifest.json
  • Cursor: ai-tools/agent-packs/cursor/rules.md
  • Claude Code: ai-tools/agent-packs/claude/CLAUDE.md
  • Windsurf: ai-tools/agent-packs/windsurf/rules.md
These are generated reference packs and onboarding aids, not the canonical source of repo governance policy.

​
Portable Skill Content Ownership

  • Canonical source: ai-tools/ai-skills/templates/*.template.md
  • Canonical template companions: ai-tools/ai-skills/templates/*.references/**
  • Local repo skill roots are either legacy-active or local-synced in the registry; they are not the global source of truth for portable skill content.

​
Canonical Governance

Canonical policy pages:
  • Agent governance: docs-guide/policies/agent-governance-framework.mdx
  • Root and allowlist governance: docs-guide/policies/root-allowlist-governance.mdx
Approved runtime targets:
  • AGENTS.md
  • .github/copilot-instructions.md
  • .claude/CLAUDE.md
  • .cursor/rules/*.mdc
  • .windsurf/rules/*.md

​
Agent Onboarding Path

  1. Read docs-guide/policies/agent-governance-framework.mdx and docs-guide/policies/root-allowlist-governance.mdx first.
  2. Use the approved runtime target for the chosen agent family.
  3. Optionally run node tools/scripts/cross-agent-packager.js --agent-pack all to generate supplemental reference packs under ai-tools/agent-packs/.
  4. Run node tools/scripts/repo-audit-orchestrator.js --mode static --scope full as the first verification run.

​
Codex Skill Portability

  • Canonical source: ai-tools/ai-skills/templates/*.template.md
  • Local install target: $CODEX_HOME/skills (fallback: ~/.codex/skills)
  • Sync behavior: safe upsert only (creates/updates managed skills; no deletion)
  • Preferred bootstrap path: bash lpd setup --yes syncs the planning skill automatically during repo setup
Runbook: 
bash lpd setup --yes
node tools/scripts/sync-codex-skills.js --skills agentic-project-management-orchestrator
node tools/scripts/sync-codex-skills.js --check
node tools/scripts/sync-codex-skills.js
node tools/scripts/sync-codex-skills.js --skills lpd-bootstrap-and-doctor,staged-test-suite-runner --dry-run
Generated metadata:
  • agents/openai.yaml is generated deterministically for each synced skill.
  • Optional companion bundles are sourced from directories beside the template file:
    • <template-stem>.references/ syncs to references/
    • <template-stem>.scripts/ syncs to scripts/
    • <template-stem>.assets/ syncs to assets/
  • Sync is managed, not destructive:
    • managed files inside an installed skill are created or updated from the canonical template bundle
    • stale managed bundle files are pruned on resync
    • unmanaged skills and unmanaged files inside a skill folder are preserved

​
Fact-Check Research Workflow

The page-content research workflow is the active docs fact-checking skill family. Canonical operator references:
  • Internal runbook: /docs-guide/frameworks/research-skill-workflow
  • Public contributor page: /v2/resources/documentation-guide/research-and-fact-checking
  • Research-to-plan template: docs-guide/tooling/research-to-implementation-plan-template.md
Primary entrypoints: 
node tools/scripts/docs-fact-registry.js --validate --registry tasks/research/claims
node tools/scripts/docs-page-research.js --page v2/orchestrators/guides/deployment-details/setup-options.mdx --report-md /tmp/docs-page-research.md --report-json /tmp/docs-page-research.json
node tools/scripts/docs-page-research-pr-report.js --files v2/orchestrators/guides/deployment-details/setup-options.mdx,v2/orchestrators/setup/rcs-requirements.mdx,v2/orchestrators/guides/operator-considerations/business-case.mdx --report-md /tmp/page-content-research-pr.md --report-json /tmp/page-content-research-pr.json
node tools/scripts/docs-research-packet.js --nav tools/config/scoped-navigation/docs-gate-work.json --version v2 --language en --tab Orchestrators --group Guides --out tasks/reports/orchestrator-guides-review/research-guides-review
The workflow is experimental and advisory-first. Use it for factual verification, contradiction review, claim-family propagation, and research packets, not generic MDX or link hygiene. When research findings need phased execution planning rather than direct fixes, use the docs-research-to-implementation-plan follow-on skill.
Last modified on March 16, 2026