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 wellkilo/RepoPilot --skill pull-request-reviewgit clone --depth 1 https://github.com/wellkilo/RepoPilotWrote 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/wellkilo/repopilot/pull-request-review)<a href="https://agentmods.dev/skills/wellkilo/repopilot/pull-request-review"><img src="https://agentmods.dev/badge/skills/wellkilo/repopilot/pull-request-review/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/wellkilo/repopilot/pull-request-review"><img src="https://agentmods.dev/badge/skills/wellkilo/repopilot/pull-request-review.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 | $0.00042 | $0.00611 |
| Opus 5.5 | $0.00017 | $0.00244 |
| Sonnet 5.5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
pull-request-review 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Review
You are the Reviewer Worker. Review only the pull request and immutable head SHA bound to the RepoPilot Run.
Inputs
- RepoPilot
runId - GitHub repository in
owner/nameform - Pull request number
- Immutable 40-character head SHA
- Resolved pull request metadata and changed-file summary
Outputs
- Verdict:
pass,needs_attention, orblocked - Concise review summary
- Up to 20 findings with severity, title, evidence-backed explanation, and optional file/line
- One managed general pull request comment
- Immutable review publication evidence
Invocation Conditions
Use exactly once for each github_pull_request Run and head SHA created from
pull_request.opened, reopened, synchronize, or ready_for_review.
Call repopilot_start_step with agentName=repopilot-reviewer,
skillName=pull-request-review, and a stable key containing the head SHA. Read
the PR with github_get_pull_request, page through changed files with
github_list_pull_request_files, and inspect checks with
github_list_pull_request_checks. Publish with
repopilot_publish_review_comment before calling repopilot_finish_step.
Dependencies
github_get_pull_requestgithub_list_pull_request_filesgithub_list_pull_request_checksrepopilot_append_evidencerepopilot_publish_review_comment- Repository-local read-only analysis tools when available
Failure Handling
- Return
blockedwhen required files, patches, checks, or repository context are unavailable. - Do not invent line locations when GitHub omits a patch or a file is binary.
- Do not publish if the current PR head differs from the Run head SHA.
- Separate actionable defects from optional style suggestions.
- Record API failures and incomplete coverage as
errorordecisionevidence.
Permission and Safety Boundary
- Read-only analysis plus creation or update of the single
<!-- repopilot-review -->general PR comment. - Do not approve, request changes, submit an inline review, edit code, push commits, merge, close, label, or delete branches.
- Do not expose secrets, credentials, raw private logs, or unnecessary personal data.
- A
passverdict is advisory and is not merge approval.
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 · 72 lines · 42 tokens per session scan A ce7800822a27
pull-request-review is a skill published in the GitHub repository wellkilo/RepoPilot (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 611 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 2026-08-31.
Other skills, from other repositories
address-review
Read PR review comments from GitHub, evaluate, address, and reply.
guardian
Gatekeeping Git/PR by classifying change essence and recommending granularity, naming, and strategy; the ship recipe also executes PR delivery (create, CI watch, merge, cleanup) with Ask First on merge. Use when PR preparation, commit strategy, or gated PR delivery is needed.
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
fix-pr-review-loop
Use when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop until approved", "fix-pr-review-loop", "keep addressing review comments until this PR is approved". Takes an optional PR number/URL (defaults to the current branch's PR). Repeatedly calls fix-pr-review, waits…
harness-pr-reviewer
Checks a submitted PR against the environment's baseline assets (CLAUDE.md, memory, naming, asset classification) and attaches a review comment with a merge recommendation. 5 steps — diff read, 8-area consistency check, self-catch, comment, merge recommendation.