github-format-standards

A guide for preparing a project to share on GitHub, a service for hosting and collaborating on code. It audits the project, improves documentation, and adds common contribution and issue files when needed.

In plain words
What is it for?
It helps review filenames and folders, update the README, check .gitignore coverage, and create files such as a license, contribution guide, and issue or pull-request templates.
Why use it?
Projects shared publicly can contain clutter, missing instructions, unsafe files, or inconsistent structure. The checks make the repository easier to use and maintain.

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/hawkongz/github-format-standards/github-format-standards
Any agent
npx skills add hawkongz/github-format-standards --skill github-format-standards
Clone the repo
git clone --depth 1 https://github.com/hawkongz/github-format-standards

Made for: Claude Code, Codex.

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,331 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00156 $0.04331
Opus 5 $0.00078 $0.02166
Sonnet 5 $0.00031 $0.00866
Haiku 4.5 $0.00016 $0.00433

Measured yesterday against content hash 29fb58b01e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-format-standards 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 yesterday.

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.

`mkdir -p ... && curl -o ... raw.githubusercontent.com/...`
SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Format Standards

When the user wants to share a project on GitHub, run the full pipeline. Take action directly — don't just recite rules.

Full Pipeline (7 Phases)

Phase 1: Root Directory Audit

Check the project root for cleanliness:

  • Red flags: large files (>1MB), temp files (*.tmp, *.bak, ~*), build artifacts (dist/, build/, *.pyc), personal config (.env, credentials.*, *.pem), IDE cruft (.vscode/, .idea/)
  • If found: warn the user and add them to .gitignore
  • Ensure .gitignore exists and covers at minimum: node_modules/, __pycache__/, *.pyc, .env, .DS_Store, dist/, build/, IDE dirs
Root audit:
  ⚠  node_modules/ found — added to .gitignore
  ✓  No large files, no secrets, no build artifacts
  ✓  .gitignore created with 12 rules

Phase 2: File Naming & Directory Structure

Naming rules:

  • All lowercase, hyphens (my-project) or underscores (my_project) — pick one style per project
  • No spaces, no Chinese characters in file/directory names (unless the project IS multilingual docs)
  • Scripts: scripts/, examples: examples/, docs: docs/, tests: tests/ or __tests__/, source: src/ or lib/
  • Fix violations immediately — rename files, move things into proper directories

Structure enforcement:

project/
├── src/           # source code (or lib/)
├── tests/         # test files (or __tests__/)
├── docs/          # documentation (optional, may use README instead)
├── scripts/       # utility scripts
├── examples/      # example usage
├── README.md
├── LICENSE
├── .gitignore
└── CONTRIBUTING.md

If the project is small (single script), the flat structure is fine — don't over-engineer.

Phase 3: Document Audit & Fix

Go through every .md file and fix:

  • Headings: # Title not #Title, no level skipping (######)
  • Code blocks: every ``` has a language tag
  • Tables: separator row has :--- alignment markers
  • Lists: consistent marker (* preferred), 2-space sub-indent
  • Commands: every shell command has an explicit interpreter (python script.py not ./script.py; bash script.sh not ./script.sh; powershell ... for Windows-specific commands). The reader should never guess how to run a command.
  • Links: no bare URLs, every image has alt text
  • Chinese spacing: 使用 GitHub not 使用GitHub; 支持 10 个 not 支持10个
  • Proper nouns: GitHub not github, JavaScript not Javascript
  • File endings: exactly one trailing blank line
  • Image paths: relative or CDN, never absolute local paths
  • No vague/informal expressions: replace "你懂的", "you know the drill", "just works" with precise instructions. Use clean macOS / Linux: format for platform labels, never "you already know 😄"

Read the full file on GitHub · 289 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. yesterday First seen · 289 lines · 156 tokens per session scan A 29fb58b01e47

Subscribe to this mod's changes

github-format-standards is a skill published in the GitHub repository hawkongz/github-format-standards (2 stars, last pushed 2mo ago), licensed MIT. It adds 156 tokens to every session and 4,331 once invoked, about $0.0008 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

format-markdown

Formats Markdown files consistently using project-native tooling first (repo scripts/config), then safe fallback formatters, and verifies the result with lint/check commands. Invoked when the user asks to format markdown, tidy docs, normalize README files, or fix markdown style drift.

soulcodex/agentic · 56 tokens

markdown-linter-fixer

Fix markdownlint errors in markdown files using markdownlint-cli2. Use when asked to "markdown linter fixer", "run markdownlint", "fix markdown lint errors", "fix MD029", or "resolve ordered list issues" across one or more .md files.

s2005/markdown-linter-fixer-skill · 60 tokens

decided-capture

Capture a NEW decision or requirement from a conversation (an interview) into ONE valid RAC (requirements-as-code) artifact — you interview and propose, the human ratifies, decided validate closes, and promotion into the trusted corpus is by pull request reviewed by someone other than the author. Use when a user wants…

asdecided/core · 113 tokens

decided-import

Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…

asdecided/core · 98 tokens

decided-review

Review and triage a RAC (requirements-as-code) corpus using the decided CLI — work prioritised findings worst-first until validation and relationship checks pass. Use when asked to review, triage, or fix findings across a project's AsDecided corpus (the decisions/ directory).

asdecided/core · 59 tokens

decided-artifacts

Author and maintain RAC (requirements-as-code) Markdown artifacts — requirements, decisions, roadmaps, prompts, designs — using the decided CLI. Use when asked to create, read, validate, update, or link AsDecided (RAC) artifacts in a project's decisions/ directory.

asdecided/core · 62 tokens