docs

docs is a command for Claude Code from azrtydxb/procoder. It costs 22 tokens per session (681 once invoked), scanned A, original, Apache-2.0.

A documentation report checks references, diagrams, links, API comments, badges, README structure, and published documentation pages. Mermaid is a text format for diagrams.

In plain words
What is it for?
Use it to review and update project documentation, public API comments, README content, badges, external links, and Pages-related documentation setup.
Why use it?
It reveals broken links, diagrams that do not compile, outdated explanations, missing documentation, and tools that could not run.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the procoder plugin — 1 skill, 34 commands shipped together

Good fit Use it to review and update project documentation, public API comments, README content, badges, external links, and Pages-related documentation setup.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/azrtydxb/procoder/docs
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/azrtydxb/procoder

Made for: Claude Code.

Or install procoder, the plugin that ships this one along with the rest of its 1 skill, 34 commands.

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 docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/azrtydxb/procoder/docs/github.svg)](https://agentmods.dev/commands/azrtydxb/procoder/docs)
Your own site
<a href="https://agentmods.dev/commands/azrtydxb/procoder/docs"><img src="https://agentmods.dev/badge/commands/azrtydxb/procoder/docs/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.

agentmods 80×15 button for docs

Your own site · 80×15
<a href="https://agentmods.dev/commands/azrtydxb/procoder/docs"><img src="https://agentmods.dev/badge/commands/azrtydxb/procoder/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 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 $0.00022 $0.00681
Opus 5.5 $0.00009 $0.00272
Sonnet 5.5 $0.00004 $0.00136
Haiku 4.5 $0.00002 $0.00068

Measured 1mo ago against content hash db06dc34b3d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs 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 1mo 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.

.kilo/commands/docs.md · 58 lines

What it actually says

The user invoked /procoder:docs with arguments: $ARGUMENTS

The command below is the procoder binary on PATH.

First read .procoder/docs/RULES.md and follow it — the repo's rules win over any defaults. If it is missing, get the default via procoder templates, write it (and .procoder/docs/mermaid.json), then continue.

  1. Run procoder docs --external and read the whole report.
  2. BLOCK lines are yours to fix before the work is finished: broken relative references, Mermaid diagrams that do not compile, dead external links, files NOT checked because a tool is missing (run procoder init).
  3. info lines are judgment calls, judged honestly:
    • drift ("doc mentions changed file X"): open the doc, verify the prose is still true; update it if not, and say so either way.
    • missing doc comments: write real doc comments for the symbols that are genuinely public API; say why for any you leave.
    • missing required docs / badges / README structure: write them. The README's first screen must sell the project — one-line USP, badges, quick start a stranger can paste.
    • a page serving two purposes at once: split it. See below.
    • Pages findings: if Pages is off or stale, check the docs CI job and gh api repos/{owner}/{repo}/pages; fix the pipeline, not the symptom.
  4. Re-run procoder docs --external and show the user the report. Repeat until no BLOCK lines remain and every info line is fixed or explained.

Never mark a doc updated without reading what it actually says (P-CONTROL: the tools diagnose, you verify and write).

Writing, not just checking

When you WRITE documentation — a new page, a rewrite, a section — the rules file governs, and its core is the Divio documentation system: there are four kinds of document, and a page that is two of them serves neither.

Name the kind before the first line:

  • Tutorial — teaches a newcomer. It must run exactly as written on a clean machine. No trade-offs, no alternatives; they lose the learner.
  • How-to guide — one stated goal, numbered steps, competence assumed. Put the goal in the title.
  • Reference — describes, never persuades. Flat, complete, boring. All the options, not the interesting ones.
  • Explanation — why it is like this: context, trade-offs, the road not taken. No steps; link to the how-to instead.

Then write it the way it gets read: answer first, a copy-pasteable example over a paragraph about one, real names (payments-api, not foo), short sentences, bold on the term the eye should land on, the searchable synonym included, and an explicit "Common pitfalls" list wherever a feature has a known misuse.

If the reader would have to be two people at once, the page is two pages.

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. 1mo ago First seen · 58 lines · 22 tokens per session scan A db06dc34b3d3

Subscribe to this mod's changes

docs is a command published in the GitHub repository azrtydxb/procoder (211 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 681 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.