GitHub product documentation writing helps create developer guides, explanations, troubleshooting pages, and security guidance in an approachable style.

Use it to draft, rewrite, or review documentation for a developer workflow, from the initial goal through setup, action, troubleshooting, and confirmation.

It keeps instructions accurate about prerequisites, permissions, supported environments, product limits, and verification steps.

github-docs — Skill for Claude Code and Codex by Neeeophytee

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 Neeeophytee/agent-stylebooks --skill github-docs

Clone the repo

git clone --depth 1 https://github.com/Neeeophytee/agent-stylebooks

Made for: Claude Code, Codex.

Or install agent-stylebooks, the plugin that ships this one along with the rest of its 16 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/github-docs/github.svg)](https://agentmods.dev/skills/neeeophytee/agent-stylebooks/github-docs)

Your own site

<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/github-docs"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/github-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/neeeophytee/agent-stylebooks/github-docs"><img src="https://agentmods.dev/badge/skills/neeeophytee/agent-stylebooks/github-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 661 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00661
Opus 5.5	$0.00023	$0.00264
Sonnet 5.5	$0.00011	$0.00132
Haiku 4.5	$0.00006	$0.00066

Measured 2mo ago against content hash 28b2e1693377, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-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 2mo 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/github-docs/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub docs

Help developers complete a product workflow with accurate, approachable guidance.

Establish the contract

Preserve commands, UI labels, permissions, plan or product availability, code, versions, and security consequences.
Do not claim a feature exists for a plan, host, or version without evidence.
Distinguish a supported workflow from a workaround or community convention.
Surface missing facts as review questions.

Design the page

Name the reader's goal in the title and opening.
State prerequisites, permissions, supported environments, and risks before the reader reaches a dependent action.
Give only enough concept to make the action understandable and safe.
Present the shortest supported path first. Place alternatives in separate sections.
Close the loop with verification, troubleshooting, or a useful next step.

Write for developers

Address the reader as you and keep the tone calm and collaborative.
Use active voice and concrete verbs. Name the component that performs an automatic action.
Define product-specific terms on first use and keep terminology stable.
Put the most important qualifier near the claim it limits.
Explain why a step matters when the reason affects security, data, or the choice between alternatives.
Use inclusive language and examples that do not assume geography, identity, or a single development environment.
Separate normative instructions from optional suggestions.

Write procedures

Begin steps with imperative verbs and use one main action per step.
State the location before the control when the reader must navigate to it.
Keep commands copyable. Explain substitutions and show the expected output only when it helps verify success.
Put warnings directly before irreversible or security-sensitive actions.
Offer recovery paths that state what data or configuration may change.

Make the page scannable

Use sentence case and front-load meaningful words in headings.
Use descriptive link text instead of generic destinations.
Use numbered lists for sequences, bullets for options, and tables for repeated comparisons with the same fields.
Use backticks for code and literal technical elements. Use bold for visible UI labels.
Keep notes exceptional. Move essential information into the main flow.

Read the full file on GitHub · 74 lines

Files

What ships with it

2 files 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.

2mo ago First seen · 74 lines · 57 tokens per session scan A 28b2e1693377

Subscribe to this mod's changes

github-docs is a skill published in the GitHub repository Neeeophytee/agent-stylebooks (78 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 661 once invoked, about $0.0002 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.

Claude Code Writing and docs agent-skills content-design documentation gemini-cli openai-codex

github-docs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
github-docsNeeeophytee/agent-stylebooks	Skill	78	2mo ago	MIT	A	57	Claude Code, Codex
readmethuanvd378/write-me-a-readme	Skill	2	3mo ago	MIT	A	103	Claude Code, Codex
yapperdzan314/yapper	Skill	1	6mo ago	MIT	A	54	Claude Code, Codex
spec-kitty-charter-doctrinePriivacy-ai/spec-kitty	Skill	1.7k	19d ago	MIT	A	135	Claude Code, Codex
mongodb-query-optimizerfcakyon/claude-codex-settings	Skill	1.2k	yesterday	Apache-2.0	A	98	Claude Code
chisle-auditJayPokale/Chisle	Skill	741	14d ago	MIT	A	130	Claude Code
crane-shotcafe3310/public-agent-skills	Skill	256	yesterday	Apache-2.0	A	25	Claude Code, Codex