review-pr

review-pr is a command for Claude Code from srbryers/slope. It costs 0 tokens per session (699 once invoked), scanned A, original, MIT.

A structured code-change review command for a pull request or current branch. It checks the changes through relevant review areas such as correctness, security, design, and user experience.

In plain words
What is it for?
Reviewing pull requests, selecting review depth, checking code and architecture, finding security issues, and tracking fixes.
Why use it?
It replaces an ad-hoc review with a tracked process that records findings and updates the sprint scorecard.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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/srbryers/slope/review-pr
Clone the repo
git clone --depth 1 https://github.com/srbryers/slope

Made for: Claude Code.

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 review-pr

README.md
[![agentmods](https://agentmods.dev/badge/commands/srbryers/slope/review-pr.svg)](https://agentmods.dev/commands/srbryers/slope/review-pr)
Your own site
<a href="https://agentmods.dev/commands/srbryers/slope/review-pr"><img src="https://agentmods.dev/badge/commands/srbryers/slope/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 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 5.1 $0.00000 $0.00699
Opus 5 $0.00000 $0.00349
Sonnet 5 $0.00000 $0.00140
Haiku 4.5 $0.00000 $0.00070

Measured 6d ago against content hash 066b112454da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/claude-code/commands/review-pr.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review PR — Structured Implementation Review

Run a structured implementation review with finding tracking and scorecard amendment.

Arguments

  • $ARGUMENTS — optional: PR number, file path, or review tier override (light/standard/deep)

Steps

1. Determine review scope

  • If a PR number was provided, use gh pr view <number> to get the diff
  • Otherwise, use git diff main...HEAD to see all changes on the current branch
  • Count tickets, packages touched, and complexity factors

2. Get review recommendations

Run slope review recommend to see which review types are suggested based on the sprint characteristics. The output will suggest review types like:

  • architect — module boundaries, data model, coupling, integration points
  • code — correctness, edge cases, bugs, unused code, runtime safety
  • security — auth, injection, secrets, OWASP top 10
  • ux — user experience, accessibility, flow coherence

3. Start review tracking

Run slope review start to initialize review state. This auto-detects the tier from the plan, or you can override with --tier=<tier>.

4. Run reviews

Launch review agents in parallel based on the recommendations. For each review type:

  1. Code Quality Review (always): Staff engineer perspective — correctness, edge cases, bugs, unused code, runtime safety, error handling
  2. Architecture Review (if recommended): Staff architect perspective — module boundaries, data model extensibility, coupling, constants management, integration points, testing strategy
  3. Specialist Reviews (if recommended): Domain-specific reviews based on the sprint's work area

Each review agent should:

  • Read all changed files
  • Analyze against its specialty area
  • Produce findings with: review_type, ticket_key, severity (minor/moderate/major/critical), description

5. Record findings

For each finding from the reviews, run:

slope review findings add --type=<type> --ticket=<key> --severity=<sev> --description="<desc>"

Read the full file on GitHub · 77 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.

  1. 6d ago First seen · 77 lines · 0 tokens per session scan A 066b112454da

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository srbryers/slope (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 699 tokens. 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.