What is external-pr-review?

A procedure for reviewing pull requests from contributors outside the repository. A pull request is a proposed code change, and the procedure checks its details, changes, tests, and compatibility.

Use it to inspect an external pull request, write the review and recommendation, verify the result, and archive the completed documents.

It gives external contributions a consistent review record and keeps them separate from internal task work.

external-pr-review — Skill for Claude Code and Codex by postmelee

Install

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.

Any agent

npx skills add postmelee/hyper-waterfall --skill external-pr-review

Clone the repo

git clone --depth 1 https://github.com/postmelee/hyper-waterfall

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/postmelee/hyper-waterfall/external-pr-review.svg)](https://agentmods.dev/skills/postmelee/hyper-waterfall/external-pr-review)

Your own site

<a href="https://agentmods.dev/skills/postmelee/hyper-waterfall/external-pr-review"><img src="https://agentmods.dev/badge/skills/postmelee/hyper-waterfall/external-pr-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 894 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00060	$0.00894
Opus 5	$0.00030	$0.00447
Sonnet 5	$0.00012	$0.00179
Haiku 4.5	$0.00006	$0.00089

Measured 7d ago against content hash 1cba25ded3c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

external-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 7d 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.

templates/locales/en/mydocs/skills/external-pr-review/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

External Contributor PR Review

Trigger

The task requester explicitly says "review PR #N" or "review external PR."
This SKILL is invoked directly.

Preconditions

The PR under review is opened from an external contributor fork to this repository's {BASE_BRANCH} or agreed base.
Do not use this SKILL for internal task PRs such as publish/task{N}. Internal tasks use the normal stage procedure.
gh CLI authentication is available.

Procedure

Collect PR metadata.

gh pr view {N} --json number,title,state,baseRefName,headRefName,headRepository,mergeable,mergeStateStatus,reviewDecision,labels,body
gh pr diff {N} | head -200
gh pr checks {N}

Check linked Issues, base/head, mergeability, and CI state.

Write review document: mydocs/pr/pr_{N}_review.md.
- Use central template mydocs/_templates/external_pr_review.md.
- Only if the template cannot be read, use these fallback sections:
  - PR information: number, author, base/head, linked Issue
  - Change summary
  - Impact area and compatibility: FFI, build, documentation
  - Code/documentation review findings
  - Verification plan
  - Recommendation: merge / request changes / close
  - Approval request to task requester
Request task requester approval for the review direction.
If needed, write a modification/verification plan: mydocs/pr/pr_{N}_review_impl.md.
- Use central template mydocs/_templates/external_pr_review_impl.md.
- Use this only when this repository needs additional verification work.
- Request approval after writing it.
Run verification only when applicable.
- Apply {PROJECT_VALIDATION_GUIDE} based on change type.
Write final report: mydocs/pr/pr_{N}_report.md.
- Use central template mydocs/_templates/external_pr_report.md.
- Include review result, verification result, final recommendation, and GitHub PR comment body or link.
After task requester approval, post the comment or review to the GitHub PR. The task requester decides merge.

When processing is complete, archive documents.

git mv mydocs/pr/pr_{N}_review.md mydocs/pr/archives/
git mv mydocs/pr/pr_{N}_review_impl.md mydocs/pr/archives/  # if it exists
git mv mydocs/pr/pr_{N}_report.md mydocs/pr/archives/

Commit once or by review phase. External PR review does not force the internal stage format.
```
git commit -m "PR #{N} review: {summary}"
```

Read the full file on GitHub · 82 lines

Changes

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.

7d ago First seen · 82 lines · 60 tokens per session scan A 1cba25ded3c2

Subscribe to this mod's changes

external-pr-review is a skill published in the GitHub repository postmelee/hyper-waterfall (79 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 894 once invoked, about $0.0003 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.

Code review agent-skills agentic-workflow ai ai-agents harness harness-engineering

md-audit

Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…

chaitanyagiri/munder-difflin · 85 tokens

storozh

Advisory semantic guard over a changeset manifest before it lands in shared state. Use after a multi-repo session produces a changeset-manifest (mirabilis C1) and before the co-sign push gate — classify each unit's routing against the darwin routing-policy (C3) and NLI-check each unit against the shield corpus (claims…

AlexShchuka/neuro-matrix · 104 tokens

generator-evaluator-loop

Orchestrate a Coder→Quality iteration loop against a story's Verification contract. Use when a story has a complete Verification section and is ready for execution with automated review.

usefulmove/enso · 40 tokens

review-before-commit

Run a behavioral self-check before persisting story results. Verifies diff simplicity, scope adherence, and verifiable completion against enso §10 behavioral principles. Use when a story's implementation is complete and ready to close.

usefulmove/enso · 49 tokens

adversarial-review

Run an independent audit gate before any fleet output lands. Use after agent-fleet-orchestration Stage 3 (or any multi-agent build) — before merge, before deploy, before the next phase. Frames the reviewer as an external adversary, not a helper; produces triaged findings with human triage for load-bearing blockers.

AlexShchuka/neuro-matrix · 72 tokens

evaluator-review-contract

Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

redker56/auto-harness · 30 tokens