A GitHub Pull Request review workflow that combines repository linters with human-style reasoning. A Pull Request is a proposed change submitted for review before it is merged; the workflow waits for one human approval before posting findings.

Use it to inspect GitHub pull requests, run whatever supported linters are installed, assess issues the tools miss, and post approved findings.

It removes repetitive lint and security-check work from the reviewer while keeping attention on correctness, cross-file behavior, and justified exceptions. It can review one or several pull requests in isolated workspaces.

pr-review — Skill for Claude Code and Codex by CiscoDevNet/essentials

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 CiscoDevNet/essentials --skill pr-review

Clone the repo

git clone --depth 1 https://github.com/CiscoDevNet/essentials

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/ciscodevnet/essentials/pr-review/github.svg)](https://agentmods.dev/skills/ciscodevnet/essentials/pr-review)

Your own site

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

Your own site · 80×15

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

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,807 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	$0.00121	$0.02807
Opus 5.5	$0.00048	$0.01123
Sonnet 5.5	$0.00024	$0.00561
Haiku 4.5	$0.00012	$0.00281

Measured 1mo ago against content hash d9b96137285c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/create_review_worktree.sh, scripts/find_review_requests.sh, scripts/lib.sh, …), 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/ess/pr-review/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review PR

Review one or more GitHub Pull Requests. Linters find, the LLM judges: a scan script runs the repo's own linters over each PR diff and emits a compact report, so you spend attention on correctness, cross-file logic, and disable-comment justification — not on re-deriving lint findings token by token.

This skill is variadic: it always operates on a set of PRs of size N ≥ 1. A single PR is just N = 1 and uses a fast in-place path; multiple PRs each get an isolated read-only worktree. Nothing is posted to any PR until you approve at one gate.

Phase: Review

Quick start

/pr-review https://github.com/<owner>/<repo>/pull/456   # one PR
/pr-review 456                                          # one PR, bare number
/pr-review 456 461 470                                  # several PRs
/pr-review                                              # discover: PRs awaiting my review

Prerequisites

GitHub CLI (gh) — authenticated, with access to the repo. Primary integration.
The current directory must be a git repo (.git/ present).
Linters are optional: the scan runs whatever is installed (ruff, pylint, bandit, eslint) and records the rest as "not run". In this repo Python linters run via uv.
TypeScript/eslint needs the workspace deps hoisted to the repo-root node_modules — run npm install once at the repo root. Until then the scan records eslint as "not run" with that hint and continues.
For N > 1, openssl and (ideally) jq are used to create and provision isolated worktrees. GitHub MCP is an optional alternative for posting (see references/github-cli.md); gh is the default.

Workflow

1. Resolve the set of PRs

Build the list of PR numbers to review, then let N = its length.

Refs given (one or many): each arg is a full URL (https://github.com/<owner>/<repo>/pull/<N>) or a bare number. Extract owner/repo from URLs; for bare numbers use gh repo view --json nameWithOwner --jq .nameWithOwner.
No refs: discover PRs awaiting your review:

Read the full file on GitHub · 243 lines

Files

What ships with it

16 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.

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.

1mo ago First seen · 243 lines · 121 tokens per session scan A d9b96137285c

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository CiscoDevNet/essentials (7 stars, last pushed 16d ago), licensed Apache-2.0. It adds 121 tokens to every session and 2,807 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 2026-09-04.

Code review Git and workflow bot docker es6 eslint framework javascript

triage-contributor-pr

Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…

prisma/orm · 131 tokens

pr-review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Review PR

Quick start

Prerequisites

Workflow

1. Resolve the set of PRs

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

triage-contributor-pr

review-implement-phase

review-triage-phase

compiler-commit

review

hero-diff-highlight