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.
npx skills add MassLab-SII/open-agent-skills --skill githubgit clone --depth 1 https://github.com/MassLab-SII/open-agent-skillsWrote 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.
[](https://agentmods.dev/skills/masslab-sii/open-agent-skills/github)<a href="https://agentmods.dev/skills/masslab-sii/open-agent-skills/github"><img src="https://agentmods.dev/badge/skills/masslab-sii/open-agent-skills/github/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/masslab-sii/open-agent-skills/github"><img src="https://agentmods.dev/badge/skills/masslab-sii/open-agent-skills/github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.06940 |
| Opus 5.5 | $0.00018 | $0.02776 |
| Sonnet 5.5 | $0.00009 | $0.01388 |
| Haiku 4.5 | $0.00004 | $0.00694 |
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 1mo 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.
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.
How it starts
The opening of the file, as written. The whole thing — 749 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Skill
This skill provides complete GitHub repository management capabilities using MCP GitHub tools.
Core Concepts
- Skill: Meaningful combinations of multiple tool calls, encapsulated as independent Python scripts
- Basic Tools: Single function calls for atomic operations via
run_github_ops.py
I. Strategy: Skills vs Tools (Read First)
1. Skill-First Strategy
Always prioritize Skill Scripts over atomic tools. Skills encapsulate best practices and error handling.
| Goal | Recommended Skill | Why? |
|---|---|---|
| Multi-file Edits | file_editor.py batch |
Atomic commit; prevents partial updates |
| Content Investigation | github_detective.py |
Unified interface for all investigation tasks |
| GitFlow Operations | gitflow_manager.py |
Enforces naming conventions and correct workflow |
| PR + Label Management | pr_manager.py update |
Handles labels atomically with PR updates |
| Issue + Label | issue_manager.py update |
Handles labels atomically with issue updates |
| CI/CD Setup | workflow_builder.py |
Full automated pipeline (branch → PR → merge) |
| Release Preparation | release_manager.py |
Automates version bump, changelog, and merge |
| Project Config | config_generator.py |
Standardized templates and configurations |
2. When to Use Basic Tools
Only use run_github_ops.py when:
- Unique Filtering: Need specific API filters not exposed by skills
- One-off Read: Quick check of file SHA or content
- Custom Operations: Operations not covered by any skill
3. GitHub Domain Coverage
This skill covers the following GitHub task categories:
| Category | Covered By |
|---|---|
| File CRUD | file_editor.py, basic file tools |
| Issue Management | issue_manager.py |
| PR Management | pr_manager.py |
| Label Management | issue_manager.py, pr_manager.py (integrated) |
| Branch Management | gitflow_manager.py, basic branch tools |
| Commit Investigation | github_detective.py |
| PR Investigation | github_detective.py |
| Repository Exploration | github_detective.py |
| CI/CD Workflows | workflow_builder.py |
| Release Management | release_manager.py |
| Config Generation | config_generator.py |
What ships with it
13 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.
- scripts/comment_manager.py 6.7 KB runs code
- scripts/config_generator.py 14 KB runs code
- scripts/file_editor.py 17 KB runs code
- scripts/gitflow_manager.py 8.1 KB runs code
- scripts/github_detective.py 29 KB runs code
- scripts/github_tools.json 4.6 KB
- scripts/issue_manager.py 24 KB runs code
- scripts/pr_manager.py 17 KB runs code
- scripts/release_manager.py 22 KB runs code
- scripts/run_github_ops.py 5.2 KB runs code
- scripts/test_utils.py 13 KB runs code
- scripts/utils.py 65 KB runs code
- scripts/workflow_builder.py 18 KB runs code
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.
- 1mo ago First seen · 749 lines · 44 tokens per session scan A b7c1135c692c
github is a skill published in the GitHub repository MassLab-SII/open-agent-skills (134 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 6,940 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
ct-dev-workflow
Development workflow orchestration for task-driven development with atomic commits, conventional commit messages, and systematic release processes. Enforces task traceability, branch discipline, smart test scope selection, and GitHub Actions integration. Use when committing code, creating releases, managing branches…
smith-build
Autonomous build phase — generates tasks, implements, tests, commits, pushes, merges, and produces release notes. Runs without user interaction.
git-ship
An automated Git release workflow that takes code changes through a branch, commit, pull request, review checks, squash merge, and return to the main branch. A pull request is a request to review and merge changes into a shared branch.
auto-build-loop
Autonomous build driver after SDD spec approval: phase-scoped headless build sessions, driver-owned commits, cross-provider review gates, milestone pauses, and fail-closed escalation — under explicit opt-in autonomy profiles.
git-workflow
Branching strategies, conventional commits, PR templates, and merge vs rebase guidance. Activate when starting features, creating PRs, or managing releases.