lint

lint is a command for Claude Code from Guohao1020/docs-cockpit. It costs 16 tokens per session (786 once invoked), scanned A, original, MIT.

A documentation checker that validates metadata and writing conventions in project Markdown files without rebuilding the dashboard. Metadata here means the structured fields placed at the start of a document.

In plain words
What is it for?
Checking every module and concept document, grouping errors by file, and reporting fixes for invalid fields, formatting issues, and optional polish suggestions.
Why use it?
It finds documentation problems before a commit or in continuous integration, without requiring a full dashboard render.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the docs-cockpit plugin — 3 skills, 5 commands, 1 hook shipped together

Good fit Checking every module and concept document, grouping errors by file, and reporting fixes for invalid fields, formatting issues, and optional polish suggestions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/guohao1020/docs-cockpit/lint
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Guohao1020/docs-cockpit

Made for: Claude Code.

Or install docs-cockpit, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 1 hook.

Wrote 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.

agentmods badge for lint

README.md
[![agentmods](https://agentmods.dev/badge/commands/guohao1020/docs-cockpit/lint.svg)](https://agentmods.dev/commands/guohao1020/docs-cockpit/lint)
Your own site
<a href="https://agentmods.dev/commands/guohao1020/docs-cockpit/lint"><img src="https://agentmods.dev/badge/commands/guohao1020/docs-cockpit/lint.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00786
Opus 5 $0.00008 $0.00393
Sonnet 5 $0.00003 $0.00157
Haiku 4.5 $0.00002 $0.00079

Measured 7d ago against content hash 0b20be86256a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lint 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 7d 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.

commands/lint.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explicit invocation of docs-cockpit lint — check every module / concept MD against the references/schema.md spec. Reports error (won't render at all) · warn (renders but UX problems) · hint (polish suggestions), each with a concrete fix + reference to the relevant schema section.

Why this command exists

docs-cockpit render writes HTML + emits validation issues. But sometimes you just want to know "is my frontmatter clean?" without rebuilding — e.g. before a commit, in CI, or when iterating on a single MD file. That's lint.

What this slash command does

When user invokes /docs-cockpit:lint:

  1. Run docs-cockpit lint from project root (default config: docs-cockpit.yaml)
  2. If exit code 0 + no output → confirm: "✓ All modules / concepts pass schema spec."
  3. If exit code 0 with hints → show hints, mention they're optional polish
  4. If exit code 1 (errors) → surface the structured output:
    • For each ❌ error block: file · field · message · suggested fix · 📚 see reference
    • Group by file (a module with 3 issues groups as one block)
    • Then offer: "Want me to fix these using the docs-cockpit-build skill (Phase 5-6: conversation + commit), or do you want to review them first?"
  5. Always end with the summary line: "X error(s) · Y warning(s) · Z hint(s) · reference: references/schema.md"

Argument handling

  • /docs-cockpit:lint (no args) → default · human-readable output
  • /docs-cockpit:lint --json → JSON output (for piping to CI / IDE)
  • /docs-cockpit:lint --strict-warn → upgrade warnings to errors (CI strict mode)
  • /docs-cockpit:lint <path-to-yaml> → use a non-default config

What you (Claude) should do with the output

The validator output is structured — each issue has 5 fields you should surface in order:

❌ <filename> · <field>: <message>
   💡 fix: <suggestion>
   📚 see: references/schema.md · <section>

Don't paraphrase these into vague advice — the precision is the point. The user can grep for the field name, look up the reference section, and fix once and forever.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 7d ago First seen · 53 lines · 16 tokens per session scan A 0b20be86256a

Subscribe to this mod's changes

lint is a command published in the GitHub repository Guohao1020/docs-cockpit (2 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 786 once invoked, about $0.0001 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.