documentation

documentation is a skill for Claude Code, Codex from richardcb/oh-my-gemini. It costs 43 tokens per session (1,270 once invoked), scanned A, original, MIT.

A guide for documenting features after they have been implemented. It treats the working code as the source of truth and covers comments, README changes, and developer guides.

In plain words
What is it for?
Use it after feature work or when asked to add documentation, update a README, explain implementation details, or create maintenance guidance.
Why use it?
It prevents documentation from describing plans or behavior that the code does not actually provide.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Gemini CLI.

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/richardcb/oh-my-gemini/documentation
Any agent
npx skills add richardcb/oh-my-gemini --skill documentation
Clone the repo
git clone --depth 1 https://github.com/richardcb/oh-my-gemini

Made for: Claude Code, Codex.

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 documentation

README.md
[![agentmods](https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/documentation.svg)](https://agentmods.dev/skills/richardcb/oh-my-gemini/documentation)
Your own site
<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/documentation"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/documentation.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,270 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 5.1 $0.00043 $0.01270
Opus 5 $0.00022 $0.00635
Sonnet 5 $0.00009 $0.00254
Haiku 4.5 $0.00004 $0.00127

Measured 6d ago against content hash 90030f3a1566, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

skills/documentation/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Skill

Goal

Create comprehensive, practical documentation for newly implemented features. Help users understand what the feature does and help developers maintain and extend it.

Activation Triggers

  • User asks to "document", "write docs", or "add documentation"
  • After completing feature implementation
  • User asks to update README or GEMINI.md

Core Principle

The code is the source of truth. Use PRD and plan for context only—document what was actually built, not what was planned.

Process

1. Understand the Implementation

# Find changed files
git diff --name-only HEAD~10 2>/dev/null

# Get summary of changes
git log --oneline -10 2>/dev/null

# Find the feature's main files
find src -name "*.ts" -newer [plan_file] 2>/dev/null | head -20

2. Identify Documentation Needs

Questions:

  • What does a user need to know to use this feature?
  • What does a developer need to know to maintain/extend it?
  • What patterns or conventions were established?
  • Where does this fit in existing documentation?

3. Determine Documentation Locations

Based on feature scope:

Code Comments (Always Required)

Add inline documentation for:

  • Complex algorithms or business logic
  • Non-obvious implementation decisions
  • Public APIs, functions, or classes
  • Important type definitions
README Files (For Significant Changes)

Update if the feature:

  • Changes how to run or deploy
  • Adds new dependencies
  • Changes architecture significantly
  • Adds major user-facing capabilities
Developer Guides (For New Patterns)

Create if the feature:

  • Introduces new patterns to reuse
  • Implements a new system component
  • Requires specific knowledge to maintain
  • Establishes conventions for others
GEMINI.md (For AI Context)

Update if the feature:

  • Introduces new commands
  • Adds new directories
  • Establishes new patterns
  • Changes tech stack

Documentation Standards

Code Comments

Use JSDoc format for TypeScript/JavaScript:

Read the full file on GitHub · 251 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. 6d ago First seen · 251 lines · 43 tokens per session scan A 90030f3a1566

Subscribe to this mod's changes

documentation is a skill published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,270 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.