github-repo

github-repo is a skill for Claude Code, Codex from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 31 tokens per session (3,259 once invoked), scanned A, original, Apache-2.0.

A set of standards and workflows for preparing, maintaining, and publishing high-quality GitHub repositories. It covers repository structure, README files, automated checks, package releases, and privacy and security audits.

In plain words
What is it for?
It is for creating or preparing open-source repositories, improving README files, configuring CI/CD, publishing NPM packages, and checking code before pushing it to GitHub.
Why use it?
It helps prevent local paths, API keys, copied repository details, and other unwanted data from being published. It also provides consistent guidance for documentation, testing workflows, and releases.

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/hybridlabor-api/bdb-dev-optimized-agent-skills/github-repo
Any agent
npx skills add hybridlabor-api/bdb-dev-optimized-agent-skills --skill github-repo
Clone the repo
git clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skills

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 github-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/github-repo.svg)](https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/github-repo)
Your own site
<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/github-repo"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/github-repo.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,259 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 $0.00031 $0.03259
Opus 5 $0.00015 $0.01630
Sonnet 5 $0.00006 $0.00652
Haiku 4.5 $0.00003 $0.00326

Measured yesterday against content hash 04b1228e11b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-repo 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 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.

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-repo/SKILL.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Repo Skill: Public-Grade Repository Standards & Release Workflows

The github-repo skill establishes strict standards for building, organizing, sanitizing, and maintaining production-ready GitHub repositories. It serves as a sister skill to openwiki-skill: while openwiki-skill manages deep wiki documentation in .openwiki/ and continuous updates, github-repo governs repository layout, top-tier README design, CI/CD pipelines, NPM release workflows, and strict privacy/security audits.


1. When to Invoke This Skill

  • Repository Initialization: When creating a new repository or preparing an existing codebase for open-source publication.
  • Pre-Push Sanitization Audit: Before committing or pushing code, to ensure no absolute local paths, API keys, foreign repository names, or cloned user metadata are published.
  • Workflow Setup: Setting up automated testing (ci.yml), automated NPM releases (publish.yml), or .gitignore rules.
  • README Overhaul: Restructuring a project's README.md to conform to modern BDB DEV corporate open-source standards.

1.1 ⚡ Mandatory Prerequisite: Automatic OpenWiki Check

Whenever the github-repo skill is invoked, the agent MUST perform an automated pre-flight check:

  1. Check .openwiki/ Existence: Verify if .openwiki/ directory exists and contains quickstart.md, architecture.md, and release notes.
  2. Automatic Execution of openwiki-skill: If .openwiki/ is missing, empty, or stale, automatically invoke openwiki-skill first before performing repo structure or README edits.
  3. Handshake: Allow openwiki-skill to scan the codebase and populate .openwiki/, then resume github-repo tasks (README layout, dynamic badges, CI/CD workflows, sanitization audit).

2. 🔒 Mandatory Sanitization & Privacy Rules (Clean-Repo Engine)

Before pushing any commit to GitHub, execute this 5-point sanitization audit:

Rule 1: No Absolute Local Paths or Usernames

  • Forbidden: Paths like /Users/john/projects/..., C:\Users\dev\..., /home/ubuntu/....
  • Allowed: Relative paths (./src/index.ts, config/settings.json) or environment placeholders (~/.config/, $HOME/).

Read the full file on GitHub · 341 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 · 341 lines · 31 tokens per session scan A 04b1228e11b5

Subscribe to this mod's changes

github-repo is a skill published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 7d ago), licensed Apache-2.0. It adds 31 tokens to every session and 3,259 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 2026-09-03.