Docs Cockpit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Docs Cockpit (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
English · 中文
<p align="center"> <img src="site/assets/brand/docs-cockpit-logo.png" alt="docs-cockpit logo" width="520"> </p>
A skill-first project cockpit for AI coding agents. Turn AI-written markdown into a schema-validated, single-file dashboard.
docs-cockpit cockpit hero
AI coding power users generate a lot of useful project markdown: plans, specs, RFCs, module notes, subtasks, and status summaries. Without structure, that knowledge becomes a pile of files your next agent session has to rediscover.
docs-cockpit turns those markdown files into an operational cockpit:
state.json sidecar that agents and CI can read without scraping HTML.The core rule is simple: cognition lives in skills, Python only renders. Your agent reasons about associations and anchors; the CLI deterministically renders markdown into docs/index.html and docs/state.json.
Install the plugin for your agent, open a repository, and ask it to set up docs-cockpit. In any project with docs-cockpit.yaml, the SessionStart hook injects the router skill automatically.
codex plugin marketplace add Guohao1020/docs-cockpit
codex plugin add docs-cockpit@docs-cockpit/plugin marketplace add Guohao1020/docs-cockpit
/plugin install docs-cockpit@docs-cockpitIf you only want the renderer and validator:
pip install docs-cockpit
docs-cockpit init
docs-cockpit render -c docs-cockpit.yamlOpen docs/index.html with file://. Run docs-cockpit lint before committing frontmatter changes.
docs-cockpit dashboard Kanban
docs-cockpit workflow overview
docs-cockpit has three layers:
docs-cockpit render writes:
docs/index.html - the self-contained dashboard.docs/state.json - machine-readable payload plus validation issues.docs/prompts.js - prompt snippets used by dashboard copy actions.No server is required at runtime.
docs-cockpit browse.references/schema.md.The plugin ships three skills:
| Skill | Role |
|---|---|
use-docs-cockpit | Entry router injected by SessionStart in projects with docs-cockpit.yaml. |
docs-cockpit-build | First-build workflow: ensure config, discover docs, infer associations, verify anchors, ask before uncertain writes, draft missing docs, render. |
docs-cockpit-rebuild | Refresh workflow: read current state, diagnose drift, re-infer broken links, apply minimal diffs, render and verify. Also answers pure status questions from state.json. |
The knowledge layer lives in references/: schema, association method, operations, config reference, design tokens, and frontmatter conventions.
Every render writes docs/state.json next to the dashboard. It contains the same payload the UI uses plus structured issues[] from validation. Agents use it for status narratives. CI can use it with strict validation. External tooling can consume it without parsing HTML.
The sidecar schema is additive-only: new fields can appear, but existing fields are not removed casually.
file://, commit it, or share it without hosting.references/schema.md is the spec the validator cites.your-project/
├─ docs-cockpit.yaml
├─ docs/
│ ├─ index.html
│ ├─ state.json
│ ├─ browse.html
│ ├─ spec/
│ │ ├─ module/M01-*.md
│ │ └─ concept/C01-*.md
│ ├─ plans/YYYY-MM-DD-<id>-plan.md
│ ├─ RFC/001-*.md
│ └─ PRD.md
├─ CLAUDE.md
└─ .git/---
id: M07
type: module
title: "Job / Task FSM"
status: in-progress
sprint: M1.2
progress: 60
desc: "Job lifecycle state machine that drives worker scheduling."
owner: harvey
docs:
- title: "Execution plan"
path: "docs/plans/2026-05-03-m07-fsm-plan.md"
depends_on: [M06]
blocks: [M08, M09]
subtasks:
- title: "Wire FSM enum to Pydantic"
done: true
- title: "Worker pulls next state from queue"
done: false
---
# Module notesChecklist items in the body can also carry anchors:
- [ ] Implement retry transition @code:src/worker/fsm.py:42-89 @docs:docs/RFC/004.md#section-2See references/schema.md for the full frontmatter and anchor spec.
Ask your agent to update docs-cockpit, or run:
docs-cockpit upgradeThe upgrade flow checks the CLI and plugin layers, shows relevant release notes, clears the plugin cache when skills changed, and prompts for the required Codex restart.
git clone https://github.com/Guohao1020/docs-cockpit
cd docs-cockpit
pip install -e .
py -3.13 -m pytest tests/ -q
docs-cockpit render -c docs_cockpit/examples/minimal.yaml --debugRead CLAUDE.md before changing architecture, skills, schema, hooks, or templates. Skill changes are release events because cached plugin descriptions affect routing.
Bug fixes and documentation improvements are welcome as PRs. Open an issue first for schema changes, new commands, workflow changes, or breaking behavior.
references/schema.mddocs/plans/P-skill-first-pivot.mdMIT. See LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.