github

A set of tools for working with GitHub through its API, including repositories, issues, pull requests, branches, releases, and automated workflows. GitHub is a service for hosting code and coordinating software development.

In plain words
What is it for?
Use it to inspect and manage repositories, issues, pull requests, branches, CI workflows, releases, reviews, collaborators, labels, milestones, notifications, stars, forks, and gists.
Why use it?
It lets an assistant perform GitHub tasks while handling multiple connected accounts by their labels. This avoids manually switching between GitHub pages for common project-management and code-review work.

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

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,159 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 $0.00048 $0.11159
Opus 5 $0.00024 $0.05580
Sonnet 5 $0.00010 $0.02232
Haiku 4.5 $0.00005 $0.01116

Measured 2d ago against content hash 7decb09d7b6e, 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (plugin/index.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/defaults/workspace/brain/cerebellum/github/SKILL.md · 1,278 lines

How it starts

The opening of the file, as written. The whole thing — 1,278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub

Interact with GitHub repositories, issues, pull requests, branches, CI, releases, gists, collaborators, labels, milestones, reviews, notifications, stars, forks, and more.

Connections

GitHub access is organized into connections. Each connection is one GitHub account the user linked, identified by a label they chose (for example Work or Personal). The label is how you — and the user — tell one account apart from another.

  • Call github_connections to see the configured labels and which account each points to. It never returns tokens.
  • Pass the chosen label as the connection parameter on every other github_* tool call.
  • You may omit connection only when exactly one connection is configured. When several exist and you don't pass one, the tool returns an error listing the available labels — read it and retry with the right label.
  • Match the label to the user's intent: "my work github" → the connection labeled Work; "my personal account" → Personal. If it is genuinely ambiguous which the user means, ask them before acting.

Authentication

Set your Personal Access Token (PAT) in Settings > Services > GitHub. The token needs the repo scope for full repository access. For public repos only, public_repo is sufficient. For gists, add gist. For deleting repos, add delete_repo. For notifications, add notifications. For listing organization membership (github_list_user_orgs), add read:org.

When to use each tool

  • Repos: github_list_repos to browse your repos, github_list_user_orgs to see which orgs you belong to, github_list_org_repos to browse an org's repos, github_get_repo for details, github_create_repo to create
  • User: github_get_authenticated_user to find out who the token belongs to — useful to resolve "my" repos or as the owner arg
  • Issues: github_list_issues to browse, github_get_issue for full detail + comments, github_create_issue to file, github_close_issue to close
  • Comments: github_list_comments_on_issue for just the discussion thread (lighter than github_get_issue), github_add_comment to post a comment
  • Labels: github_list_labels to see available labels, github_create_label to add one, github_add_labels_to_issue to tag issues/PRs
  • Milestones: github_list_milestones to see project milestones, github_create_milestone to add one
  • PRs: github_list_prs to browse, github_get_pr for full detail + diff stats, github_create_pr to open, github_update_pr to edit title/body/state/base, github_merge_pr to merge
  • PR reviews: github_list_pr_reviews for review status, github_request_reviewers to request reviews
  • PR files: github_list_pr_files for the file-level diff summary (pairs well with github_get_pr for a full review picture)
  • Branches: github_list_branches to see all, github_delete_branch to remove merged branches
  • CI: github_get_workflow_runs for run status, github_get_workflow_run_logs for failure details, github_rerun_workflow to retry, github_cancel_workflow_run to stop, github_dispatch_workflow to trigger manually
  • Releases: github_list_releases to browse, github_get_release for full detail + assets, github_create_release to publish
  • Commits: github_get_commit for details on a specific commit, github_compare_commits to see the diff between two refs
  • Code: github_search_code to find code across GitHub, github_get_file_content to read a specific file
  • Collaborators: github_list_collaborators to see who has access, github_add_collaborator to invite, github_remove_collaborator to revoke
  • Topics: github_list_repo_topics to see tags, github_replace_repo_topics to update them
  • Gists: github_list_gists to browse, github_create_gist to share snippets
  • Notifications: github_list_notifications to check what needs attention, github_mark_notifications_read to clear
  • Stars: github_list_stargazers to see who starred a repo, github_star_repo / github_unstar_repo to manage stars
  • Forks: github_fork_repo to fork a repo into your account or an org

Read the full file on GitHub · 1,278 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.

  1. 2d ago First seen · 1,278 lines · 48 tokens per session scan A 7decb09d7b6e

Subscribe to this mod's changes

github is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 11,159 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 2026-08-31.

Related

Other skills, from other repositories

agent-computer-use

REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…

kortix-ai/agent-computer-use · 216 tokens

claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

warpdotdev/warp · 193 tokens

create-skill

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

warpdotdev/warp · 64 tokens

gui-integration-test

GUI desktop app only. Writes, runs, and debugs Warp integration tests using the custom Builder/TestStep framework in crates/integration. Use when adding a new integration test, fixing a failing integration test, wiring a test into the manual runner or nextest suite, or verifying end-to-end UI and terminal behavior in…

warpdotdev/warp · 72 tokens

gui-onboarding-verification-skill

GUI desktop app only. Launch two parallel Oz cloud agents with computer use to download and install the latest stable Linux Warp build, capture screenshots while walking through first-time onboarding in both logged-out and logged-in states, then selectively fan out follow-up cloud agents for distinct onboarding…

warpdotdev/warp · 98 tokens

logging-and-error-reporting

How and when to log (log:: levels, safe macros) and report errors to Sentry (reporterror!) in the Warp codebase. Use when adding or reviewing any logging or error reporting — picking a log level, deciding log vs. reporterror!, keeping sensitive data out of logs, or surfacing an error to Sentry.

warpdotdev/warp · 75 tokens