pr-review

pr-review is a command for coding agents from AcKeskin/contexture. It costs 39 tokens per session (322 once invoked), scanned A, original, MIT.

A local pull-request review command for GitHub. A pull request is a proposed set of code changes; this command fetches its diff and checks correctness, design, security, and review hygiene without posting comments.

In plain words
What is it for?
Use it with the current branch or a specified pull-request number to review GitHub changes. It produces findings, a summary, and an actionable checklist.
Why use it?
It provides a structured way to inspect proposed changes before they are merged. It keeps the review results local and can focus on the whole request or selected paths.

Command

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.

agentmods
npx agentmods add commands/ackeskin/contexture/pr-review
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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.

agentmods badge for pr-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/ackeskin/contexture/pr-review.svg)](https://agentmods.dev/commands/ackeskin/contexture/pr-review)
Your own site
<a href="https://agentmods.dev/commands/ackeskin/contexture/pr-review"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 322 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00322
Opus 5 $0.00019 $0.00161
Sonnet 5 $0.00008 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 3d ago against content hash 3588bc5d5e70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

commands/pr-review.md · 25 lines

What it actually says

Run the pr-review skill.

Forms:

  • /pr-review — auto-detect PR from the current branch.
  • /pr-review <number> — review a specific PR by number.
  • /pr-review <number> <path...> — review only the given paths within the PR.

Examples:

  • /pr-review — review the PR associated with the current branch.
  • /pr-review 123 — review PR #123.
  • /pr-review 123 src/auth/ — review only auth-related changes in PR #123.
  • /pr-review 456 src/api/ src/services/ — review api and services changes in PR #456.

The skill fetches PR data via gh pr view and gh pr diff, asks whether to load architectural rules via skills/discover/SKILL.md and whether the user has specific guidelines or context, then scans the diff across four categories: code correctness & bugs, design & patterns, PR hygiene, and security. Findings are grouped by file with severity and concrete suggestions, followed by a summary table and an actionable review checklist. Output is local only — no comments are posted to GitHub.

Does not auto-fire. Not a replacement for /review (which audits local code for architectural drift).

See ~/.claude/skills/pr-review/SKILL.md for the full procedure.

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.

  1. 3d ago First seen · 25 lines · 39 tokens per session scan A 3588bc5d5e70

Subscribe to this mod's changes

pr-review is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 322 once invoked, about $0.0002 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 2026-08-31.