github

A workflow guide for working on an existing GitHub repository, such as fixing a bug, adding tests, or opening a pull request. A pull request is a request for the repository's maintainers to review and merge code changes.

In plain words
What is it for?
Use it when you name a GitHub repository and want to clone it, inspect its project setup, modify code, add tests, or prepare a pull request.
Why use it?
It checks whether GitHub access is configured before work begins. This avoids making changes that cannot later be pushed or submitted for review.

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

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 956 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 $0.00000 $0.00956
Opus 5 $0.00000 $0.00478
Sonnet 5 $0.00000 $0.00191
Haiku 4.5 $0.00000 $0.00096

Measured yesterday against content hash 9ae289c2f066, 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 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.

docker/docs/skills/github/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: GitHub (existing-repo workflow)

Use when the user names a GitHub repo to work on ("fix the bug in acme/widgets", "add tests to my-org/api", "open a PR against octocat/hello-world for the spelling issue").

Precondition: is GitHub bound?

Check the env array in the sandbox_create response (or the sandbox env later). If GITHUB_TOKEN is present, GitHub is wired: the gh CLI, git over HTTPS, and every GitHub SDK that respects GITHUB_TOKEN will Just Work without further setup.

If GITHUB_TOKEN is NOT there, stop and tell the user:

GitHub isn't bound on this cluster yet. Run agentry service bind github from your CLI (you'll be prompted for a Personal Access Token), then ask me to retry.

Do NOT try to clone a repo without a token — the clone will work for public repos but every push will fail with a confusing 403, which is worse than a clean "not configured" message.

Workflow

1. command_run "gh repo clone OWNER/REPO /workspace/projects/REPO"
2. command_run "cd /workspace/projects/REPO && git config user.email [email protected] && git config user.name $GITHUB_USERNAME"
3. Detect the project kind from /workspace/projects/REPO contents:
     - package.json with "next" dep      → kind=nextjs
     - package.json (any other)          → kind=custom (read start_command from package.json scripts)
     - app.py with `import streamlit`    → kind=streamlit
     - app.py with `from fastapi import` → kind=fastapi
     - requirements.txt + no entry app   → kind=python-script
     - .html + assets only               → kind=static-html
     - else                              → kind=custom (ask user for start_command)
4. project_create name=REPO kind=<detected> — this writes
   .sandbox-project.json without touching the cloned source.
5. project_start name=REPO and iterate normally.

project_create writes the manifest into the cloned dir without clobbering existing files — its starter-file scaffolding only fills in files that don't already exist, so a real repo just gets the manifest layer.

Read the full file on GitHub · 86 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 · 86 lines · 0 tokens per session scan A 9ae289c2f066

Subscribe to this mod's changes

github is a skill published in the GitHub repository agentry-ai/agentry (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 956 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens