Manages llmdoc projects: activates for llmdoc/ folders, initializes/updates docs and knowledge, handles architecture/workflows/conventions, integrates Codex CLI hooks.
From llmdocnpx claudepluginhub tokenrollai/llmdoc --plugin llmdocThis skill is limited to using the following tools:
references/codex-cli-hooks.mdreferences/design-goals.mdreferences/doc-structure.mdreferences/operating-protocol.mdreferences/templates.mdreferences/update-and-memory.mdtemplates/codex-hooks.jsontemplates/session-start.shtemplates/stop.shDesigns and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
This skill is the operating system for llmdoc projects.
Use it whenever:
llmdoc/SessionStart or Stop hooks to reinforce the workflowRead these references in order:
references/design-goals.mdreferences/operating-protocol.mdreferences/doc-structure.mdreferences/update-and-memory.mdThen load only the specific extras you need:
references/templates.md for document templatesreferences/codex-cli-hooks.md for Codex CLI hook supportllmdoc/index.md, then llmdoc/startup.md, then the MUST files it lists.guides/ and memory/reflections/ before non-trivial edits.worker, aligns with the user before non-trivial edits./llmdoc:update..llmdoc-tmp/, not llmdoc/memory/.recorder owns stable docs, memory/decisions/, and memory/doc-gaps.md. reflector owns memory/reflections/.Codex CLI SessionStart and Stop hook support lives here:
references/codex-cli-hooks.mdtemplates/codex-hooks.jsontemplates/session-start.shtemplates/stop.shUse hooks to reinforce the workflow, not to replace judgment.