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 Orkas-AI/Orkas-Awesome-AgentSkills --skill github-maintainergit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/github-maintainer)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/github-maintainer"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/github-maintainer/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/orkas-ai/orkas-awesome-agentskills/github-maintainer"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/github-maintainer.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 | $0.00003 | $0.00754 |
| Opus 5 | $0.00002 | $0.00377 |
| Sonnet 5 | $0.00001 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
github-maintainer 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Maintainer
Use this when the user wants maintainer-grade judgment over a GitHub project queue. The goal is not just to list issues or pull requests; it is to decide what each item means, what evidence exists, what is risky, and what should happen next.
Scope
- Default to the current repository when the working directory is a GitHub checkout.
- Broaden to multiple repositories only when the user asks for broad, all, everything, a named owner, or a named organization.
- Read local project guidance first when available:
CONTRIBUTING.md,README.md, maintainer notes, roadmap, project policy files, or equivalent docs. - Use live GitHub data through
ghwhen queue state matters. - Only comment, close, merge, rerun CI, or push changes after explicit user approval.
Workflow
- Identify the repository and confirm access.
- Collect open issues and pull requests.
- Inspect enough detail to explain each surfaced item.
- Classify each item by type, fit, risk, proof, blocker, and next action.
- Include trust signals for non-maintainer contributors when recommending action.
- If the user asks to act, work one item at a time and verify before moving on.
References
- Read
references/issue-pr-triage.mdfor queue discovery, item evaluation, trust signals, and output structure. - Read
references/permissions-and-safety.mdbefore any write action or autonomous project-maintenance work. - Use
scripts/github-activity.shwhenghandjqare available and contributor trust history is useful.
Default Output
For current-repository triage:
Repo: owner/name
Source: gh commands and local files inspected
Immediate:
- #123 PR: title
What: one-line plain-language summary.
Type/Fit/Risk: bug|feature|dependency|docs|internal; good|mixed|poor; low|medium|high because ...
Trust: factual contributor signal, or unavailable.
Proof: CI, tests, reproduction, diff review, or missing proof.
Blocker: none, missing access, failing check, unclear product direction, stale branch, no repro, etc.
Next: exact maintainer action.
Needs judgment:
- #124 issue: ...
Defer/close:
- #125 issue: ...
Skipped:
- Reason and scope limitation.
What ships with it
3 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.
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.
- 9d ago First seen · 80 lines · 3 tokens per session scan A 38d75361fda7
github-maintainer is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (13 stars, last pushed 2mo ago), licensed MIT. It adds 3 tokens to every session and 754 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
contribute
Complete contribution workflow using git-town. Create branch → commit → PR → ship. Preflight at every step.
pull-request-automation
Audits and improves the pull request workflow for a GitHub repository. Covers PR description templates, auto-labelling, CODEOWNERS, PR size checks, and branch protection rules. Invoked when the user asks to improve the PR process, set up PR automation, or add a PR template.
code-review-loop
Use when opening a PR for review or when receiving review feedback. Activate for keywords like "code review", "PR review", "request review", "review feedback", "address comments", "reviewer said". Covers both ends of the loop: preparing a reviewable PR and acting on feedback rigorously. Always engage with every…
finalize-pr
Automatically finalize pull requests for merge by resolving CodeQL violations, review threads, merge conflicts, and CI failures. Handles single PR (current branch or by number), all open PRs in the repo, or all open PRs across the org. Includes bot-authored PRs in all modes.
resolve-pr-threads
Orchestrates resolution of GitHub PR review threads AND reads recent non-thread PR comments (top-level + review bodies) by grouping related feedback, processing each group sequentially inline with superpowers:receiving-code-review, and resolving threads via GraphQL. Use when you need to batch-process review feedback…
pr-sweep
Use when open pull requests have piled up in one repo or across an owner's repos and you want the pile triaged and driven toward zero in one pass — including when most of them are bot- or teammate-authored. Also use when a sweep must run many repos in parallel without racing approvals or flooding CI.