agentmods.dev

github-workflows

A workflow for handling GitHub repository work from start to finish, including authentication, issues, pull requests, code review, continuous integration checks, and releases.

In plain words
What is it for?
Use it to clone or fork repositories, manage issues and pull requests, review code, investigate failed GitHub Actions checks, and prepare or merge releases.
Why use it?
It gives coding agents a consistent way to inspect and change GitHub projects while checking access and repository state before making changes.

Skill for Claude CodeCodex

2 1mo ago A scan 41 tokens original MIT
View the source file dirtybits/agent-skills
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/dirtybits/agent-skills/github-workflows
Any agent
npx skills add dirtybits/agent-skills --skill github-workflows
Clone the repo
git clone --depth 1 https://github.com/dirtybits/agent-skills

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,176 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 $0.00041 $0.02176
Opus 5 $0.00020 $0.01088
Sonnet 5 $0.00008 $0.00435
Haiku 4.5 $0.00004 $0.00218

Measured yesterday against content hash df2c6f030d3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-workflows 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.

The scan reads SKILL.md. This mod also ships 1 executable file (references/absorbed-packages/github-auth/scripts/gh-env.sh), 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.

skills/github-workflows/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Workflows

Overview

This umbrella replaces narrow GitHub skills with one class-level workflow. Load it whenever the task involves GitHub state or Git repository work that will touch GitHub: authentication, cloning/forking, issues, PRs, code review, CI, releases, or API fallbacks.

Prefer the gh CLI when authenticated. Fall back to git plus GitHub REST/GraphQL with $GITHUB_TOKEN when gh is missing or lacks a scope.

When to Use

  • Set up or troubleshoot GitHub auth.
  • Clone, fork, create, or inspect repositories.
  • Create, triage, label, or comment on issues.
  • Implement work on a branch and open/update/merge a PR.
  • Review a PR or request a pre-commit review before pushing.
  • Inspect codebase size/languages before planning repository work.
  • Diagnose or monitor GitHub Actions / CI failures.

Do not use for generic local debugging unless GitHub state matters; use systematic-debugging or the software-development umbrella for pure local work.

Operating Pattern

  1. Discover repository context. Run git remote -v, git status --short --branch, and derive OWNER/REPO from the GitHub remote.
  2. Check auth before side effects. Prefer gh auth status; otherwise locate $GITHUB_TOKEN from the environment or ~/.hermes/.env. Never claim a push/PR/comment happened until the command returns a URL or status.
  3. Search before creating. Search existing issues and PRs for duplicates before opening new maintainer-visible artifacts.
  4. Make minimal, reviewable changes. Use a branch, conventional commits, and a clear PR body with summary + tests.
  5. Verify with real outputs. Run tests locally when possible, inspect CI status/logs, and report exact URLs/IDs.
  6. Escalate permission blockers honestly. If PAT scopes, fork permissions, or branch protections block the action, leave the branch/patch ready and explain the failed command.

Labeled Subsections from Former Narrow Skills

Auth and credentials

  • gh auth status is the fastest readiness check, but success does not guarantee push/fork/createPullRequest scopes.
  • For REST fallback, extract GITHUB_TOKEN from the environment, Hermes .env, or git credentials only for the current command context; avoid printing secrets.
  • If direct push returns 403 or fork creation says Resource not accessible by personal access token, diagnose scopes instead of retrying blindly.

Read the full file on GitHub · 119 lines

Files

What ships with it

19 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. yesterday First seen · 119 lines · 41 tokens per session scan A df2c6f030d3e

Subscribe to this mod's changes

github-workflows is a skill published in the GitHub repository dirtybits/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,176 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.

Code reviewGit and workflowSecuritycigithubpull-requestsworkflow
Related

Other skills, from other repositories

github-actions-ci

Structure GitHub Actions workflows — jobs, steps, caching, matrix builds, secrets, and a quality gate that blocks merges.

vikasudasi/skill-vault · 29 tokens

github-pr-workflow

Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.

paperclipai/paperclip · 39 tokens

writing-guidelines

This skill should be used when the user asks to "review writing", "check documentation style", "audit interface copy", or "apply writing guidelines".

fcakyon/claude-codex-settings · 34 tokens

humanize

This skill should be used when writing or revising text, including responses, documentation, comments, emails, posts, reports, and messages, especially when the user asks to "humanize", "write naturally", "remove AI tone", or "avoid AI writing".

fcakyon/claude-codex-settings · 56 tokens

create-pr

This skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as PR", "push and create PR", or explicitly invokes "create-pr".

fcakyon/claude-codex-settings · 49 tokens

dokploy-deploy

This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".

fcakyon/claude-codex-settings · 63 tokens