Documentation

Documentation is a skill for Claude Code from nxtg-ai/forge-plugin. It costs 112 tokens per session (2,211 once invoked), scanned A, original, MIT.

Standards for keeping technical documentation aligned with the code. It covers comments for functions and types, README files, change logs, API references, and checks for outdated documentation.

In plain words
What is it for?
Use it when writing or reviewing READMEs, code comments, API documentation, architecture guides, release notes, and documentation updates after code changes.
Why use it?
It reduces the risk that users and maintainers follow instructions that no longer match the software. It also gives projects a consistent structure for explaining setup, usage, and changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the nxtg-forge plugin — 27 skills, 24 commands, 33 agents shipped together

Good fit Use it when writing or reviewing READMEs, code comments, API documentation, architecture guides, release notes, and documentation updates after code changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nxtg-ai/forge-plugin/documentation
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.

Any agent
npx skills add nxtg-ai/forge-plugin --skill documentation
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 agents.

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/nxtg-ai/forge-plugin/documentation/github.svg)](https://agentmods.dev/skills/nxtg-ai/forge-plugin/documentation)
Your own site
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/documentation"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/documentation/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 Documentation

Your own site · 80×15
<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/documentation"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00112 $0.02211
Opus 5.5 $0.00045 $0.00884
Sonnet 5.5 $0.00022 $0.00442
Haiku 4.5 $0.00011 $0.00221

Measured 12d ago against content hash 24f82fb6f9ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Documentation scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

* curl -X POST https://api.example.com/users \
plugins/nxtg-forge/skills/documentation/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Management

Purpose: Keep documentation synchronized with code Primary Agent: release-sentinel (opus) — docs↔code sync, staleness, changelog generation Supporting Agent: docs (sonnet) — writes JSDoc/README/API/architecture docs Contributors: all agents (each documents its own output)


The Documentation Promise

"Every feature is documented. Every change is tracked. No user is left wondering how something works."

The doc tree below is the recommended layout for a consuming project — it is aspirational, not the structure of this plugin repo itself. Adopt the parts that fit; do not scaffold empty directories to match it.


Documentation Hierarchy

docs/
├── README.md                 # Entry point, always current
├── CHANGELOG.md              # Auto-generated from commits
├── CONTRIBUTING.md           # How to contribute
├── 
├── getting-started/          # Onboarding
│   ├── installation.md
│   ├── quick-start.md
│   └── first-project.md
│
├── guides/                   # How-to guides
│   ├── authentication.md
│   ├── deployment.md
│   └── troubleshooting.md
│
├── api/                      # API reference (auto-generated)
│   ├── overview.md
│   ├── users.md
│   ├── projects.md
│   └── webhooks.md
│
├── components/               # Component docs (auto-generated)
│   ├── button.md
│   ├── input.md
│   └── card.md
│
├── cli/                      # CLI reference (auto-generated)
│   └── commands.md
│
├── architecture/             # Design docs (manual)
│   ├── overview.md
│   ├── decisions/            # ADRs
│   │   ├── 001-database-choice.md
│   │   └── 002-auth-strategy.md
│   └── diagrams/
│
└── templates/                # Doc templates
    ├── api-endpoint.md
    ├── component.md
    └── adr.md

Documentation Types & Ownership

1. Reference Documentation (Auto-Generated)

What: API endpoints, component props, CLI commands, config options How: Extract from code annotations (JSDoc, OpenAPI, decorators) When: On every relevant code change Owner: Release Sentinel (automated)

/**
 * Create a new user account
 * 
 * @endpoint POST /api/users
 * @auth Required (Bearer token)
 * @rateLimit 10 requests/minute
 * 
 * @param {string} email - User's email address
 * @param {string} password - Password (min 8 chars)
 * @param {string} [name] - Display name (optional)
 * 
 * @returns {User} Created user object
 * @throws {400} Invalid input
 * @throws {409} Email already exists
 * 
 * @example
 * ```bash
 * curl -X POST https://api.example.com/users \
 *   -H "Authorization: Bearer <token>" \
 *   -d '{"email": "[email protected]", "password": "secure123"}'
 * ```
 */
export async function createUser(req: Request): Promise<User> {
  // Implementation
}

Read the full file on GitHub · 268 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. 12d ago Changed · +12 tokens per session 24f82fb6f9ae
  2. 1mo ago First seen · 268 lines · 100 tokens per session scan A 7fdc3036e94f

Subscribe to this mod's changes

Documentation is a skill published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 2,211 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

rag-retrieval

Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.

yonatangross/orchestkit · 58 tokens

error-analysis

Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.

yonatangross/orchestkit · 61 tokens

dev

One-command dev loop boot. Spins up portless (named HTTPS subdomain), emulate (stateful API mocks), the project's dev server, and an agent-browser session, all keyed to the current git branch. Use when starting a feature branch, switching worktrees, or returning to a project after a break. Skips silently with install…

yonatangross/orchestkit · 76 tokens

testing-llm

LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.

yonatangross/orchestkit · 55 tokens

accessibility

Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…

yonatangross/orchestkit · 65 tokens

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…

jpicklyk/task-orchestrator · 212 tokens