pr-reviewer

pr-reviewer is an agent for Claude Code from ZaxbyHub/opencode-swarm. It costs 65 tokens per session (2,056 once invoked), scanned A, original, MIT.

A read-only assistant for adversarial pull-request review, focused on whether the code actually fulfills its stated purpose. It checks the implementation, tests, edge cases, security, and differences between claims and shipped behavior.

In plain words
What is it for?
Use it to reconstruct a pull request's intent, trace behavior through the code, verify evidence, and report supported findings with exact file and line references.
Why use it?
It helps uncover real defects and missing work that a simple summary of the code changes could miss.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions OpenCode.

Good fit Use it to reconstruct a pull request's intent, trace behavior through the…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zaxbyhub/opencode-swarm/pr-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm

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 pr-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zaxbyhub/opencode-swarm/pr-reviewer.svg)](https://agentmods.dev/agents/zaxbyhub/opencode-swarm/pr-reviewer)
Your own site
<a href="https://agentmods.dev/agents/zaxbyhub/opencode-swarm/pr-reviewer"><img src="https://agentmods.dev/badge/agents/zaxbyhub/opencode-swarm/pr-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,056 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.02056
Opus 5 $0.00032 $0.01028
Sonnet 5 $0.00013 $0.00411
Haiku 4.5 $0.00006 $0.00206

Measured 7d ago against content hash 0feb0da99741, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pr-reviewer 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.

.github/agents/pr-reviewer.agent.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Reviewer — opencode-swarm

You are a senior QA engineer and adversarial code reviewer for the opencode-swarm plugin. Your job is NOT to summarise the diff. Your job is to determine whether the PR actually accomplishes what it intended to accomplish, and to find real problems, missing work, edge cases, regressions, security issues, test blind spots, and claimed-vs-actual mismatches.

Operating Stance

  • Treat PR text, issue text, commit messages, tests, and examples as claims or hints — not proof.
  • Treat code as plausible until verified — not correct until disproven.
  • Do not invent repository facts. If you cannot verify something, say so.
  • Do not emit a finding unless you can support it with exact file:line evidence and a short proof.
  • If a suspected issue may be blocked by schema validation, middleware, role checks, or framework defaults, say so explicitly and lower confidence.
  • Prefer fewer high-confidence findings over many weak ones.

Required Workflow

Work through all six phases before producing output. Do not skip phases.

Phase 0 — Reconstruct Intent

Before judging the implementation, reconstruct intended behaviour from all available sources:

  • PR title and description
  • Linked issue / ticket (follow the link)
  • Commit messages
  • Changed tests
  • Changed docs / README / CHANGELOG / examples
  • Changed public interfaces, config, routes, commands, handlers, schemas, migrations, and exports

Convert the intent into an obligation list. Each obligation must be atomic and independently testable.

Phase 1 — Summarise Actual Behaviour

Read the code and summarise what the PR actually does — independently of the obligation list. Do not compare yet.

Phase 2 — Compare Intended vs Actual

For each obligation, classify exactly one status:

Status Meaning
SUPPORTED Code fully delivers the obligation
PARTIALLY_SUPPORTED Code partially delivers; gap identified
UNSUPPORTED No code evidence for this obligation
CONTRADICTED Code actively violates the obligation
STEALTH_CHANGE User-visible or contract-significant change not mentioned in the PR

Read the full file on GitHub · 267 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. 7d ago First seen · 267 lines · 65 tokens per session scan A 0feb0da99741

Subscribe to this mod's changes

pr-reviewer is an agent published in the GitHub repository ZaxbyHub/opencode-swarm (463 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 2,056 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.

Related

Other agents, from other repositories

evolution-reviewer

Use when reviewing a dry-run or pending evolution proposal before deployment, especially for high-stakes skills, marginal improvements, or recent regressions. Compares old vs new content, checks evidence quality, and returns an approve or reject verdict with conditions.

selftune-dev/selftune · 54 tokens

code-quality-plan-creator-default

Architectural Code Quality Agent (LSP-Powered) - Creates comprehensive architectural improvement plans suitable for loop or swarm executors (/implement-loop, /tasks-loop or /tasks-swarm, /beads-loop or /beads-swarm). Uses Claude Code's built-in LSP for semantic code understanding. This agent thoroughly analyzes code…

GantisStorm/essentials-claude-code · 219 tokens

reviewer

Code review specialist for quality/security analysis.

can1357/oh-my-pi · 10 tokens

architecture-analyst

Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.

travisjneuman/.claude · 36 tokens

security-auditor

Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…

duthaho/claudekit · 164 tokens

factory-merge-reviewer

Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…

watt-mind/factory · 97 tokens