OpenParable
Skip to content
← Back to skills

Llmdoc

Documents
llmdoc

Llmdoc is an Agent Skill for documents published in the TokenRollAI/llmdoc repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Default operating skill for llmdoc-enabled projects. Use when a project has llmdoc/, when initializing llmdoc, when updating project knowledge, or when Codex CLI hooks should reinforce the workflow.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/TokenRollAI/llmdoc/blob/HEAD/skills/llmdoc/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/llmdoc, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

/llmdoc

This skill is the operating system for llmdoc projects.

Use it whenever:

  • the project already has llmdoc/
  • the user asks to initialize or update project docs
  • the task touches architecture, workflow, conventions, or doc structure
  • you want Codex CLI SessionStart or Stop hooks to reinforce the workflow

Load Order

Read these references in order:

  1. references/design-goals.md
  2. references/operating-protocol.md
  3. references/doc-structure.md
  4. references/update-and-memory.md
  5. references/lessons-learned.md

Then load only the specific extras you need:

  • references/templates.md for document templates
  • references/codex-cli-hooks.md for Codex CLI hook support

Core Rules

  • Read llmdoc/index.md, then llmdoc/startup.md, then the MUST files it lists.
  • Proactively read relevant guides/ and memory/reflections/ before non-trivial edits.
  • The main assistant, not worker, aligns with the user before non-trivial edits.
  • At the end of a non-trivial task, the main assistant should consider prompting for /llmdoc:update.
  • Temporary investigation artifacts live in .llmdoc-tmp/, not llmdoc/memory/.
  • .llmdoc-tmp/ is a local temporary context cache. It may help nearby sessions, but it is ignored by git, not indexed, and not a source of truth.
  • recorder owns stable docs, memory/decisions/, and memory/doc-gaps.md. reflector owns memory/reflections/.

Hook Support

Codex CLI SessionStart and Stop hook support lives here:

  • references/codex-cli-hooks.md
  • templates/codex-hooks.json
  • templates/session-start.sh
  • templates/stop.sh

Use hooks to reinforce the workflow, not to replace judgment.