Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Guohao1020/docs-cockpitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/guohao1020/docs-cockpit/browse)<a href="https://agentmods.dev/commands/guohao1020/docs-cockpit/browse"><img src="https://agentmods.dev/badge/commands/guohao1020/docs-cockpit/browse/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/guohao1020/docs-cockpit/browse"><img src="https://agentmods.dev/badge/commands/guohao1020/docs-cockpit/browse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00828 |
| Opus 5 | $0.00015 | $0.00414 |
| Sonnet 5 | $0.00006 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
browse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explicit invocation of docs-cockpit browse — for when the user just wants to read the project's scattered MDs in a tree-organized browser, not see a dashboard.
When to use
- User says: "我想浏览这个项目的所有文档 / give me an MD reader for this project / 把所有 md 汇总到一个 html 里"
- User wants a sidebar-tree view of
docs/adrs/,docs/plans/, etc. - The project's docs don't have frontmatter (so
docs-cockpit renderdashboard is empty) but user still wants something readable - User also wants their
~/.claude/plans/<project>/notes accessible from the same HTML
What it does
- Scans MDs in:
- Project root top-level
*.md(README, CLAUDE.md, CHANGELOG, etc.) <project>/docs/recursively~/.claude/plans/<project-name>/(if exists; skip with--no-claude)~/.claude/projects/<sanitized-cwd>/memory/(if exists)
- Project root top-level
- Groups files into "roots" by source (project / claude-plans / claude-memory)
- Embeds content as JSON in a single HTML file with:
- Sidebar: nested file tree per root, foldable, with file counts
- Main: marked.js + highlight.js renders the clicked MD
- Search: filters file paths (Ctrl+K /
/to focus) - localStorage: remembers last-viewed file + which folders are expanded
Usage
# Default · scan project + ~/.claude
docs-cockpit browse
# Specific directory only
docs-cockpit browse --dir docs/adrs --output docs/adrs.html
# Skip ~/.claude scanning
docs-cockpit browse --no-claude
# Override project name (shows in topbar)
docs-cockpit browse --project "Bastion"
Steps
- Confirm the use case. Browse mode is for READING. If user wants the project-progress dashboard (Kanban / KPI), redirect to
/docs-cockpit:renderinstead. - Run dry first (no
--dir) to see what gets scanned by default:docs-cockpit browse --output /tmp/preview.html - If too much noise, narrow with
--dir:docs-cockpit browse --dir docs/adrs --dir docs/plans --output docs/browse.html - Open the HTML in the user's browser (file://). Show them the path.
- Update flow: tell the user that re-running
docs-cockpit browseregenerates the HTML — there's no live watch. After editing MDs, re-run the command +Ctrl+Rin browser.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 64 lines · 31 tokens per session scan A d0deebd9bbb3
browse is a command published in the GitHub repository Guohao1020/docs-cockpit (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 828 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
nyann:route-docs
Change documentation storage routing (local, Obsidian, Notion, or per-type split) and regenerate the doc scaffold to match.
export-latex
Export the current paper draft to production-ready LaTeX (.tex) and PDF using the arxiv-style template. Converts draft.md + references.bib + figures/ into a complete LaTeX project with resolved citations, tables, and figures. Compiles to PDF automatically.
docs
Generate or update OpenAPI spec from existing API routes.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.