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 rp1-run/rp1 --skill pr-reviewgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/pr-review)<a href="https://agentmods.dev/skills/rp1-run/rp1/pr-review"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/pr-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/rp1-run/rp1/pr-review"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/pr-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 | $0.00025 | $0.03139 |
| Opus 5 | $0.00013 | $0.01570 |
| Sonnet 5 | $0.00005 | $0.00628 |
| Haiku 4.5 | $0.00003 | $0.00314 |
Grade A, and why
pr-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 4d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Orchestrator
§ROLE: Map-reduce PR review orchestrator. 6 phases, local + CI modes, comment deduplication.
§CTX: Use the pre-resolved projectRoot, kbRoot, and workRoot values from the generated Workflow Bootstrap section. Do not hardcode .rp1/work/ or .rp1/context/ paths.
§GUARDRAILS
- Never create git worktrees under
.rp1/work/or anywhere inside the target project's.rp1/directory. - If a separate checkout is absolutely required during review, use a temporary path outside the project artifact tree.
References
| File | Purpose | When to Load |
|---|---|---|
references/link-artifacts.md |
Reusable external link artifact registration pattern and PR review binding | During finalization phase (after P4 reporting) |
references/analysis-phases.md |
P0.5 visual gen, P1 splitting, P2 analysis, P3 synthesis, P4 reporting, P5 comment posting | After P0 resolves target and intent |
STATE-MACHINE
stateDiagram-v2
[*] --> reviewing
reviewing --> posting : analysis_complete
posting --> [*] : done
On each phase transition, report via:
rp1 agent-tools emit \
--workflow pr-review \
--type status_change \
--run-id {RUN_ID} \
--step {CURRENT_STATE} \
--data '{"status": "running"}'
RUN_IDcomes from the generated Workflow Bootstrap section- Derive
RUN_NAMEfrom the resolved PR context: use"PR #{pr_number}"when a PR number is available, otherwise use"PR: {branch_name}"as fallback - On the first emit only, include
--name "{RUN_NAME}"to label the run
On session start, emit the status change:
rp1 agent-tools emit \
--workflow pr-review \
--type status_change \
--run-id {RUN_ID} \
--name "{RUN_NAME}" \
--step reviewing \
--data '{"status": "running"}'
State Progression Protocol:
- Report each
--stepwith--data '{"status": "running"}'when you enter that state - For non-terminal states: move to the NEXT state when done (entering the next state implies the previous completed)
- For terminal states (those with
→ [*]transitions): report with--data '{"status": "completed"}'and--close-runwhen the step's work finishes - On error, transition to the appropriate failure state in the graph
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.
- 4d ago First seen · 316 lines · 25 tokens per session scan A 2e8eff374996
pr-review is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 25 tokens to every session and 3,139 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
pr-splitter
Analyse an oversized pull request or proposed branch changeset and decompose it into smaller, dependency-aware, independently reviewable pull requests. Use when a PR is too large for effective review or when the user asks to split, stack, or repackage a feature branch without changing its final behaviour. Do not use…
smart-pr-generator
Analyzes Git diffs (staged or unstaged) and generates conventional commit messages and detailed, slop-free Pull Request descriptions.
comprehensive-review-pr-enhance
You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descriptions, automate review processes, and ensure PRs follow best practices for clarity, size, and reviewability.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.