documentation

A set of instructions for keeping a software repository’s documentation accurate and aligned with its code. It covers README files, project guidance, design decisions, and other documents.

In plain words
What is it for?
Use it when editing documentation, recording architectural decisions, or shipping a code change that changes documented behavior.
Why use it?
It helps prevent documentation from claiming that planned or incomplete features already work. It also reduces confusion when code and its instructions drift apart.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/extra-org/extra/documentation
Any agent
npx skills add extra-org/extra --skill documentation
Clone the repo
git clone --depth 1 https://github.com/extra-org/extra

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00805
Opus 5 $0.00016 $0.00402
Sonnet 5 $0.00006 $0.00161
Haiku 4.5 $0.00003 $0.00081

Measured 2d ago against content hash 0a4e744404e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation 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 2d 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.

.claude/skills/documentation/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Documentation

Purpose

Keep the repository's documentation accurate, honest, and synchronized with the code, so future agents and users can trust it.

When to Use This Skill

  • Editing anything in docs/, the README.md, or AGENTS.md.
  • Adding or changing an ADR.
  • Shipping a behavior/contract change that documentation must reflect.

Files to Read First

  • AGENTS.md
  • docs/README.md (reading order and index).
  • The specific doc/ADR you are changing and any code it describes.
  • .ai/skills/skill-authoring.md if the doc is a skill.

Core Principles

  • Be honest about status. Clearly separate what exists from what is planned; use accurate status markers (✅ done / ⏳ planned).
  • Never claim unimplemented features work. The project is in the foundation phase — don't describe the runtime/compiler/API as functioning.
  • Docs follow code. Update docs in the same change as the behavior they describe; don't let them drift.
  • Decisions go in ADRs. A binding architectural decision is recorded as an ADR, not buried in prose.
  • Show, don't just tell. Prefer examples, flows, and small diagrams where they clarify.
  • Right file for the right scope: README = user-facing; AGENTS.md = repo-wide rules for agents; ADRs = architectural decisions; docs/ = design.

Process

  1. Identify scope. Decide which file(s) the change belongs in (README vs. AGENTS.md vs. docs vs. ADR) — don't scatter the same content.
  2. Write the change concisely; add an example or flow if it aids understanding.
  3. For a new binding decision, add docs/adr/NNNN-title.md using the existing ADR format (Status, Context, Decision, Consequences, Alternatives, Enforcement).
  4. Sync cross-references: update indexes (docs/README.md, .ai/README.md) and any links.
  5. Verify honesty: re-read for any claim that overstates current status.
  6. Validate with make check.

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 32 tokens per session scan A 0a4e744404e9

Subscribe to this mod's changes

documentation is a skill published in the GitHub repository extra-org/extra (108 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 805 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 2026-08-30.