documentation

Guidance for documenting existing software and systems in READMEs, runbooks, API documentation, module notes, and code comments. It focuses on describing how the code works now.

In plain words
What is it for?
Use it when writing or reviewing documentation for existing code, including Consult skill files, setup guides, operational procedures, and API or module references.
Why use it?
It keeps explanations close to the code or team responsible for them and avoids documenting behavior that does not exist. It also helps decide when code, tests, schemas, or generated references should be the source of truth.

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

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,330 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 $0.00024 $0.01330
Opus 5 $0.00012 $0.00665
Sonnet 5 $0.00005 $0.00266
Haiku 4.5 $0.00002 $0.00133

Measured 2d ago against content hash fe2bb970a3d9, 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.

agents/.agents/skills/documentation/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation

Iron Law

DOCUMENT ONLY WHAT NEEDS PROSE. KEEP DOCS NEAR THE CODE, CONTRACT, OR TEAM THAT MAINTAINS THEM.

When to Use

  • The user asks for or approves writing/reviewing READMEs, runbooks, tutorials, how-to guides, reference docs, module docs, or code comments: documentation that describes code and systems as they exist.
  • Authoring or revising Consult SKILL.md files; skills are documentation for agents and follow the same clarity rules.
  • Deciding whether prose is needed or whether a type, schema, generated reference, test, or command output should be the source of truth.

When NOT to Use

  • Forward-looking documents that record decisions or propose futures: design docs, ADRs, RFCs, tech specs, PRDs, requirements, acceptance criteria, system analyses, strategy. Consult does not cover these; use a dedicated writing skill if one is installed, such as Terse.
  • Ordinary implementation where docs might later be useful but were not requested, approved, or required by a validator. Name the possible docs gap in the final response instead of editing docs.
  • API contract design; use api.
  • Release coordination, changelog process, release notes, version manifests, or migration notes; use release. Those artifacts land only during release prep.
  • Alert mechanics and dashboards; use observability.

Core Ideas

  1. Documentation is a separate work product, not an implementation reflex. Before editing docs outside the user's request, ask whether docs are in scope unless a repo validator requires the update.
  2. Living documentation has an owner, a nearby source of truth, and a change path; orphaned prose becomes misinformation.
  3. One doc has one reader situation: tutorial, how-to, reference, explanation, or runbook.
  4. Build the reader's knowledge in layers. Name the starting point, introduce terms before relying on them, and move from prerequisite concepts to working steps to deeper reference. Do not make readers infer the path.
  5. Link to source-of-truth artifacts instead of restating generated facts. Put docs next to the code or service whose reviewers can catch drift.
  6. Write the why, context, and tradeoffs; let code/tests/schemas prove mechanics.
  7. Voice and prose structure: plain, direct, concrete sentences, no em dashes, only words that earn their place.
  8. Delete stale docs when you cannot fix them now.
  9. Comments explain why and how when names, types, schemas, tests, or local structure cannot. Encode the rule in code or tests first; add a comment only when the reason remains non-obvious.
  10. Runbooks are operational artifacts: symptom, diagnosis, remediation, verification, escalation.
  11. Large project docs use the repo's existing docs system. If none exists, choose one during scaffolding or with user approval.

Read the full file on GitHub · 120 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 120 lines · 24 tokens per session scan A fe2bb970a3d9

Subscribe to this mod's changes

documentation is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 1,330 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.

Related

Other skills, from other repositories

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

notion

Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.

elizaOS/eliza · 69 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

scaffold

Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.

SethGammon/Citadel · 44 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

organize

Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces; in-file…

SethGammon/Citadel · 66 tokens