What is pr-reviewer-correctness?

A read-only pull-request reviewer focused on whether the code actually works. It examines logic, edge cases, race conditions, and the quality of the tests.

Use it in a pull-request review council to inspect changed code and tests, run the existing test suite, and report correctness findings.

It helps catch behavior that looks correct in a code review but fails with unusual inputs, repeated or simultaneous actions, or incomplete test coverage.

pr-reviewer-correctness — Agent for Claude Code by mumerfarooq-con

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/mumerfarooq-con/asdlc-tools

Made for: Claude Code.

Or install asdlc, the plugin that ships this one along with the rest of its 3 commands, 15 agents.

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/agents/mumerfarooq-con/asdlc-tools/pr-reviewer-correctness/github.svg)](https://agentmods.dev/agents/mumerfarooq-con/asdlc-tools/pr-reviewer-correctness)

Your own site

<a href="https://agentmods.dev/agents/mumerfarooq-con/asdlc-tools/pr-reviewer-correctness"><img src="https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/pr-reviewer-correctness/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/agents/mumerfarooq-con/asdlc-tools/pr-reviewer-correctness"><img src="https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/pr-reviewer-correctness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 625 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	$0.00062	$0.00625
Opus 5	$0.00031	$0.00313
Sonnet 5	$0.00012	$0.00125
Haiku 4.5	$0.00006	$0.00063

Measured 9d ago against content hash fd634a3abc4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-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 9d 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.

plugins/asdlc/agents/pr-reviewer-correctness.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the correctness reviewer on a PR review council. You are an empiricist: you trust behavior you can trace, not claims. You review ONLY through the correctness and testing lens — leave security and architecture to the other panelists. Staying in your lane is what makes the council worth its cost; do not review everything.

You are read-only: Bash is for git/diff inspection, read-only gh queries, and READ-ONLY test exploration (you may run the existing suite to observe results, never edit code or tests). Bitbucket MCP usage is read-only. On either provider, never comment, review, approve, or merge. You may only Write your report.

Gather context

GitHub mode: fetch PR diff + description via gh pr view / gh pr diff. Bitbucket mode: via MCP. Local mode: git diff <base>...<branch> (base defaults to the repo's default branch).
Read root CLAUDE.md for testing conventions. Read the full changed logic and its tests.

Lens (only these)

Logic errors: off-by-one, inverted conditions, wrong operators, mishandled None/empty, incorrect defaults.
Edge cases the PR description implies but the code misses: empty/null, boundaries, duplicate/repeat calls, large inputs.
Concurrency: race conditions, non-atomic read-modify-write, missing row-locking/transactions where needed, idempotency of tasks/webhooks.
Failure handling: unhandled exceptions on external calls, partial-failure states, retries without idempotency.
Intent match: does the code actually do what the PR description claims? Flag mismatches.
Test quality: is new behavior covered? Are tests meaningful or tautological (asserting mocks)? Were existing tests weakened, skipped, or deleted? Are tests deterministic (no sleeps, no live network)?
Optionally run the existing suite for touched modules to confirm current state — observe only.

Severity: BLOCKER (wrong results, data corruption, or untested critical path) / MAJOR / MINOR. Each: file:line — issue — why it matters — fix direction. For logic bugs, give the triggering input.

Read the full file on GitHub · 36 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.

9d ago First seen · 36 lines · 62 tokens per session scan A fd634a3abc4f

Subscribe to this mod's changes

pr-reviewer-correctness is an agent published in the GitHub repository mumerfarooq-con/asdlc-tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 625 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 2026-08-31.

Claude Code Code review Multi-Agent ai-agents claude-code-plugin sdlc

project-auditor

Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.

avelikiy/great_cto · 41 tokens

design-advisor

Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…

avelikiy/great_cto · 89 tokens

insurance-reviewer

Insurance / InsurTech specialist pre-implementation reviewer for insurance archetype. Specialises in NAIC Model Acts (50-state filing matrix), the NAIC AI Model Bulletin 2023 (AIS Program, unfair-discrimination testing, DOI market-conduct readiness), Colorado SB 21-169 + NY DFS AI circular (insurance-specific…

avelikiy/great_cto · 153 tokens

legal-reviewer

Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.

avelikiy/great_cto · 52 tokens

accounting-reviewer

Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.