permit0: Agent for Claude Code

.github/agents/reviewer-correctness.md

reviewer-correctness is an agent for Claude Code from permit0-ai/permit0. It costs 0 tokens per session (215 once invoked), scanned A, original, Apache-2.0.

An automated reviewer that checks a GitHub pull request for correctness, security, edge cases, and test coverage. A pull request is a proposed change awaiting review.

In plain words
What is it for?
Use it to inspect a pull request, leave review comments through GitHub, and write an approval or blocking verdict to a specified file.
Why use it?
It can catch defects and missing tests before a change is approved, including cases listed in the implementation specification.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is permit0-ai/permit0's own configuration. It tells Claude Code how to work on permit0 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything permit0 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to permit0-ai/permit0. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/permit0-ai/permit0/main/.github/agents/reviewer-correctness.md
Clone the repo
git clone --depth 1 https://github.com/permit0-ai/permit0

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 reviewer-correctness

README.md
[![agentmods](https://agentmods.dev/badge/agents/permit0-ai/permit0/reviewer-correctness.svg)](https://agentmods.dev/agents/permit0-ai/permit0/reviewer-correctness)
Your own site
<a href="https://agentmods.dev/agents/permit0-ai/permit0/reviewer-correctness"><img src="https://agentmods.dev/badge/agents/permit0-ai/permit0/reviewer-correctness.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 215 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 $0.00215
Opus 5 $0.00000 $0.00108
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00021

Measured 6d ago against content hash 5d003d656258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reviewer-correctness 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.

.github/agents/reviewer-correctness.md · 18 lines

What it actually says

You are the correctness & security reviewer in the Polis automated pipeline.

Inspect the PR diff: run git diff origin/main...HEAD and gh pr view. Assess ONLY: correctness, edge cases, security, and whether the tests actually prove the behavior. Additionally verify that every case listed in the spec's ## Test plan was actually implemented as a real test, and that scripts/test.sh runs them. Use "block" if any Test-plan case is missing or unexecuted.

Submit a GitHub PR review using gh with inline comments on the specific lines where you find issues (use gh api to create a review with comments, or gh pr comment for general notes).

Then write ONLY a JSON object to the output file you are told, with this exact shape: {"verdict": "approve", "summary": "..."} or {"verdict": "block", "summary": "..."} Use "block" if there is any correctness or security defect. Keep the summary to one paragraph.

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 · 18 lines · 0 tokens per session scan A 5d003d656258

Subscribe to this mod's changes

reviewer-correctness is an agent published in the GitHub repository permit0-ai/permit0 (185 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 215 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 2026-08-30.

Related

Other agents, from other repositories

Agent Governance Reviewer

AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.

agentrust-io/awesome-ai-governance · 35 tokens

Application Security Engineer

AppSec specialist who secures the software development lifecycle through threat modeling, secure code review, SAST/DAST integration, and developer security education that makes secure code the default.

SHAdd0WTAka/Zen-Ai-Pentest · 40 tokens

Codebase Archaeologist

Multi-session, multi-tool drift detection specialist who audits codebases touched by several AI coding tools (Claude, Cursor, Copilot, Windsurf, etc.) over time, finding silent logic mismatches, dead code, and doc-vs-code divergence that no single session would ever notice on its own.

SHAdd0WTAka/Zen-Ai-Pentest · 65 tokens

Codebase Onboarding Engineer

Expert developer onboarding specialist who helps new engineers understand unfamiliar codebases fast by reading source code, tracing code paths, and stating only facts grounded in the code.

SHAdd0WTAka/Zen-Ai-Pentest · 37 tokens

Minimal Change Engineer

Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.

SHAdd0WTAka/Zen-Ai-Pentest · 50 tokens

Code Reviewer

Expert code reviewer who provides constructive, actionable feedback focused on correctness, maintainability, security, and performance — not style preferences.

SHAdd0WTAka/Zen-Ai-Pentest · 28 tokens