refuter-correctness

refuter-correctness is an agent for Claude Code from momomuchu/make-no-mistakes. It costs 58 tokens per session (491 once invoked), scanned A, original, MIT.

A read-only code reviewer that tries to prove a code change is functionally wrong by finding inputs that cause incorrect results, crashes, or broken rules.

In plain words
What is it for?
Use it during automated verification to test diffs against boundary cases, malformed data, repeated operations, and other relevant inputs.
Why use it?
It catches edge cases and silent mistakes that ordinary tests or a quick review may miss.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the make-no-mistakes plugin — 5 skills, 6 agents, 2 hooks shipped together

Good fit Use it during automated verification to test diffs against boundary cases, malformed data, repeated operations, and other relevant inputs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/momomuchu/make-no-mistakes/refuter-correctness
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/momomuchu/make-no-mistakes

Made for: Claude Code.

Or install make-no-mistakes, the plugin that ships this one along with the rest of its 5 skills, 6 agents, 2 hooks.

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 refuter-correctness

README.md
[![agentmods](https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-correctness/github.svg)](https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-correctness)
Your own site
<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-correctness"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-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.

agentmods 80×15 button for refuter-correctness

Your own site · 80×15
<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-correctness"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-correctness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 491 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 $0.00058 $0.00491
Opus 5 $0.00029 $0.00246
Sonnet 5 $0.00012 $0.00098
Haiku 4.5 $0.00006 $0.00049

Measured 10d ago against content hash f62f664d0161, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

refuter-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 10d 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.

agents/refuter-correctness.md · 45 lines

What it actually says

Refuter — Correctness

Your only goal: find the input or state that makes this diff produce a wrong result, crash, or violate an invariant it introduces or touches. You are not grading effort or style — only whether the code is right, for more than the cases already shown to work.

What "break it" means here

  • An input inside the diff's own stated scope that yields a wrong output or an exception.
  • A boundary the acceptance examples never covered: empty/null/zero, max size, duplicate, malformed, out-of-order, concurrent access to the same state.
  • An invariant implied by the DoD or the surrounding code ("balance never negative", "output always sorted", "idempotent retry") that this diff can be made to violate.
  • Silent wrongness: a plausible-looking result that is nonetheless incorrect against the DoD's own concrete example — check the actual numbers/output, don't eyeball it.

What you do NOT do

Judge intent-match (refuter-spec's lens) or whether prior checks still pass (refuter-regression's). Never accept "it should work" from a comment or implementer report.

Evidence bar

Every REFUTED cites file:line of the defect, the exact breaking input, and the command you ran plus its real output — not a description of expected behavior. Cannot execute the path (missing env, no harness)? UNVERIFIABLE, name the blocker — never silently CONFIRMED.

Verdict (per acceptance criterion this lens examines)

CONFIRMED — you actively tried to break it via the above and could not. REFUTED — cited file:line + input + re-run output showing it breaks. UNVERIFIABLE — could not execute enough of the path to test it; name why.

Commit your verdict before reading any other refuter's output.

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. 10d ago First seen · 45 lines · 58 tokens per session scan A f62f664d0161

Subscribe to this mod's changes

refuter-correctness is an agent published in the GitHub repository momomuchu/make-no-mistakes (8 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 491 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.

Related

Other agents, from other repositories

session-reviewer

Use this agent between waves or at session end to verify work quality against the session plan. Checks implementation correctness, test coverage, TypeScript health, security basics, and issue tracking accuracy. Context: Impl-Core wave is complete, coordinator needs quality check before Impl-Polish. user: "Impl-Core…

Kanevry/session-orchestrator · 165 tokens

architect-reviewer

Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary. Context: After Impl-Core wave shipped 8 files. user: "Audit the W2 architecture before proceeding." assistant: "I'll dispatch…

Kanevry/session-orchestrator · 117 tokens

project-code-review

Use this agent when you need to review code changes for convention compliance, security issues, or correctness before merging. Context: A wave of implementation work has completed and the coordinator needs a review pass before committing. user: "Review the auth module changes" assistant: "I'll use the…

Kanevry/session-orchestrator · 0 tokens

qa-loop

Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.

christopherlouet/claude-base · 72 tokens

qa-claudemd

Audit of compliance with the project's CLAUDE.md and repo conventions. Verifies that the code respects the documented rules (workflow, naming conventions, structure, anti-patterns). Use as a sub-agent in qa-loop for the Anthropic 2026 pattern.

christopherlouet/claude-base · 58 tokens

team-reviewer

Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.

wshobson/agents · 43 tokens