A pull-request review workflow for checking proposed code changes and then, if requested, applying selected fixes and posting one review on GitHub. A pull request is a request to merge one set of code changes into another branch.

Use it to inspect a pull request in a checkout or temporary worktree, record review findings, apply chosen fixes, submit the GitHub review, and clean up.

It keeps finding problems, deciding which fixes to make, and sending the review as separate steps. It also records findings and decisions so the final review is based on explicit choices.

review-pr — Skill for Claude Code and Codex by marcello-a/Planchette

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 marcello-a/Planchette --skill review-pr

Clone the repo

git clone --depth 1 https://github.com/marcello-a/Planchette

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/marcello-a/planchette/review-pr/github.svg)](https://agentmods.dev/skills/marcello-a/planchette/review-pr)

Your own site

<a href="https://agentmods.dev/skills/marcello-a/planchette/review-pr"><img src="https://agentmods.dev/badge/skills/marcello-a/planchette/review-pr/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marcello-a/planchette/review-pr"><img src="https://agentmods.dev/badge/skills/marcello-a/planchette/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,813 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	$0.00125	$0.02813
Opus 5.5	$0.00050	$0.01125
Sonnet 5.5	$0.00025	$0.00563
Haiku 4.5	$0.00013	$0.00281

Measured 7d ago against content hash e6288b027404, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-pr 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/checkouts.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/review-pr/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a pull request

This is Planchette's default review-pr skill. Planchette put it in ~/.claude/skills/review-pr because no skill of that name was there; the file .planchette-default beside this one marks it, and Planchette keeps it up to date. To use your own, replace this folder (and delete the marker): Planchette never touches a review-pr skill without the marker. Your own skill must keep the three-file contract below — the Reviews panel reads and writes nothing else.

Planchette's Reviews panel drives this skill, but it also works on its own from any terminal. The contract is three JSON files in one directory (the review dir):

File	Written by	Read by
`findings.json`	this skill, `review` mode	Planchette (shows the findings), `submit` mode
`decisions.json`	Planchette, or this skill after asking in the terminal	`submit` mode
`sent.json`	this skill, `submit` mode	Planchette (moves the row to "Sent")

Default review dir when run by hand: ~/.planchette/reviews/<owner>-<repo>-<number>/. Planchette passes --dir.

Mode — derive it from the arguments

Arguments	Mode
`<pr-url>` or `<number>` (+ flags)	`review`
`submit <review-dir>`	`submit`

Flags for review:

--dir <path> — the review dir (create it).
--keep-checkout — Planchette owns this checkout (a temporary worktree it made). Do not remove it at the end; Planchette closes its project and removes the worktree.
--checks — also install dependencies and run the repo's lint, type-check and tests for what the PR changes. Off by default: an install can take minutes.

Never commit, push or post in review mode. Never post before decisions.json exists.

`review` mode

1. Resolve the PR

gh pr view <url|number> --json number,url,title,author,state,isDraft,headRefName,headRefOid,baseRefName,headRepository,headRepositoryOwner,isCrossRepository,maintainerCanModify,additions,deletions,changedFiles

Read the full file on GitHub · 258 lines

Files

What ships with it

1 file 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.

scripts/checkouts.py 7.6 KB runs code

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 · 258 lines · 125 tokens per session scan A e6288b027404

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository marcello-a/Planchette (7 stars, last pushed 2d ago), licensed MIT. It adds 125 tokens to every session and 2,813 once invoked, about $0.0005 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 2026-10-31.

Code review Git and workflow

review-pr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
review-prmarcello-a/Planchette	Skill	7	2d ago	MIT	A	125	Claude Code, Codex
prYeachan-Heo/oh-my-claudecode	Skill	41k	yesterday	MIT	A	47	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	6d ago	MIT	A	46	Claude Code
otto-pr-review-loopomnigent-ai/omnigent	Skill	11k	yesterday	Apache-2.0	A	17	Claude Code, Codex
engram-branch-prGentleman-Programming/engram	Skill	7.8k	yesterday	MIT	A	37	Claude Code, Codex
github-contributordaymade/claude-code-skills	Skill	1.5k	yesterday	MIT	A	105	Claude Code, Codex
revdiffumputun/revdiff	Skill	945	yesterday	MIT	A	250	Claude Code