github

A command-line skill for managing GitHub, the website where developers store code and collaborate. It uses GitHub’s official gh command-line tool for repositories, issues, pull requests, releases, workflows, searches, gists, and API requests.

In plain words
What is it for?
Use it to create, clone, fork, search, and inspect repositories; manage issues and pull requests; review workflow runs; publish releases; manage gists; and make GitHub API requests.
Why use it?
It removes the need to switch between many GitHub web pages or remember separate commands for common repository tasks.

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/bug-ops/zeph/github
Any agent
npx skills add bug-ops/zeph --skill github
Clone the repo
git clone --depth 1 https://github.com/bug-ops/zeph

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,757 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 $0.00104 $0.02757
Opus 5 $0.00052 $0.01378
Sonnet 5 $0.00021 $0.00551
Haiku 4.5 $0.00010 $0.00276

Measured 2d ago against content hash df475cd1f756, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github 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 2d 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.

IMPORTANT: Always use `gh` CLI for ALL GitHub interactions. Never use `curl` with GitHub API
.zeph/skills/github/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub CLI Operations

IMPORTANT: Always use gh CLI for ALL GitHub interactions. Never use curl with GitHub API directly — gh api handles authentication, pagination, and rate limiting automatically.

Quick Reference

Category Command Details
Auth gh auth status Check login state
Auth gh auth login Interactive login
Repos gh repo view View current repo
Repos gh repo create NAME Create new repo
Repos gh repo clone OWNER/REPO Clone a repo
Repos gh repo fork OWNER/REPO Fork a repo
Issues gh issue list --limit 10 references/issues.md
Issues gh issue create --title T --body B Create issue
PRs gh pr list --limit 10 references/pull-requests.md
PRs gh pr create --title T --body B Create PR
PRs gh pr merge N Merge PR
Search gh search repos "QUERY" references/search.md
Releases gh release list --limit 5 references/releases.md
Workflows gh run list --limit 10 references/workflows.md
API gh api repos/OWNER/REPO references/api.md
Gists gh gist list --limit 10 references/gists.md
Labels gh label list List repo labels
Install brew install gh references/install.md

Authentication

# Interactive login (browser or token)
gh auth login

# Login with token (non-interactive, CI)
echo "$TOKEN" | gh auth login --with-token

# Check auth status
gh auth status

# Switch between accounts
gh auth switch

# Refresh token scopes
gh auth refresh --scopes read:project

# Logout
gh auth logout

Environment variable auth (overrides stored credentials):

Variable Purpose
GH_TOKEN / GITHUB_TOKEN Auth token for github.com
GH_ENTERPRISE_TOKEN Auth token for GitHub Enterprise

Read the full file on GitHub · 387 lines

Files

What ships with it

9 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.

  1. 2d ago First seen · 387 lines · 104 tokens per session scan A df475cd1f756

Subscribe to this mod's changes

github is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 7d ago), licensed MIT. It adds 104 tokens to every session and 2,757 once invoked, about $0.0005 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 2026-08-30.