Borrowing it
Nothing to install: this file belongs to orka-agents/orka. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/orka-agents/orka/main/.agents/skills/pr-closeout/SKILL.mdgit clone --depth 1 https://github.com/orka-agents/orkaWrote 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/orka-agents/orka/pr-closeout)<a href="https://agentmods.dev/skills/orka-agents/orka/pr-closeout"><img src="https://agentmods.dev/badge/skills/orka-agents/orka/pr-closeout.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.02122 |
| Opus 5 | $0.00043 | $0.01061 |
| Sonnet 5 | $0.00017 | $0.00424 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade A, and why
pr-closeout 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 8d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Closeout
Drive the current GitHub PR from “has feedback or failing checks” to “currently merge-ready.” Run this automatically after creating or updating an agent-authored PR unless the user opts out or the PR is intentionally draft/WIP. This orchestrates git, GitHub review threads, CI logs, local verification, and optional $autoreview; it is not a replacement for $autoreview.
Contract
- Treat CI failures and review comments as signals, not truth. Verify each against the real code path, workflow logs, and current PR diff before changing code.
- Reject stale, duplicate, speculative, invalid, or regression-causing feedback with concise GitHub evidence instead of making unnecessary changes.
- Prefer small fixes at the right ownership boundary. Do not do unrelated cleanup or broad refactors.
- If CI/comment-triggered fixes change code, rerun relevant local checks, push, and rerun the closeout snapshot until no current actionable blockers remain.
- Stop when the PR currently has no merge conflicts, required checks are green, no unresolved actionable review threads remain, and
reviewDecisionis non-blocking. Do not keep polling just to get nicer wording.
Guardrails
- Treat automatic post-PR closeout or the user’s closeout request as the scope. Fix merge conflicts, CI failures, and unresolved actionable review feedback only.
- Creating or updating an agent-authored PR authorizes normal closeout writes for that PR: push fixes to the non-main PR branch, reply on GitHub with fix/pushback evidence, and resolve review threads after replying when they are addressed. A request like “reply and resolve each comment,” “push updates,” or “drive this PR until green” authorizes the same writes.
- Do not submit reviews, merge, enable auto-merge, retarget the PR, force-push, amend, rebase, or perform destructive git operations unless explicitly asked or the branch owner’s workflow clearly requires it.
- Never push directly to
main. For PR branches, commit withgit commit -swhen a commit is needed, then push the current branch. - Redact secrets from logs and summaries. Do not paste tokens, auth URLs, JWTs, TxTokens, cookies, or credentials.
- Say “currently no unresolved actionable review threads remain,” not “reviewers will have no more comments.” Future review activity cannot be guaranteed.
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.
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.
- 8d ago First seen · 122 lines · 85 tokens per session scan A 622e168322cc
pr-closeout is a skill published in the GitHub repository orka-agents/orka (22 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 2,122 once invoked, about $0.0004 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
github-review-pr
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…
github-review-pr
Review GitHub pull requests with evidence-backed, multi-perspective analysis and false-positive filtering. Use when the user asks to review, inspect, or check a GitHub pull request by number or URL. Default to reporting findings locally; publish comments, submit reviews, or approve only when the user explicitly…
prepare-pr
End-to-end drives working-tree changes to a review-ready pull request — commit, sync base, squash to one commit, open/update the PR — then KEEPS RUNNING IN-SESSION (poll CI + code-review bots in 5-min rounds, up to 10) fixing every legitimate Critical/High finding and build failure until the PR is review-ready (never…
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
github-code-review
Review PRs: diffs, inline comments via gh or REST.
git-workflow
Conventional commits, PR creation, and quality gate verification.