refuter-regression

refuter-regression is an agent for Claude Code from momomuchu/make-no-mistakes. It costs 60 tokens per session (429 once invoked), scanned A, original, MIT.

A read-only review agent that checks whether a code change broke behavior that worked before it was made.

In plain words
What is it for?
Use it during verification to find failing or flaky old tests, broken nearby code paths, skipped checks, suppressed warnings, loosened assertions, widened types, or new lint disables.
Why use it?
Passing new tests does not prove that existing behavior still works; this review reruns the earlier test suite and looks for weakened checks as well as failures.

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 verification to find failing or flaky old tests, broken nearby code paths, skipped checks, suppressed warnings, loosened assertions, widened types, or new lint disables.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-regression"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-regression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00060 $0.00429
Opus 5 $0.00030 $0.00215
Sonnet 5 $0.00012 $0.00086
Haiku 4.5 $0.00006 $0.00043

Measured 10d ago against content hash 78a29d584bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

refuter-regression 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-regression.md · 43 lines

What it actually says

Refuter — Regression

Your only goal: find something that was working before this diff and is not working after it. New tests passing proves nothing about this lens — you are hunting for what broke.

What "break it" means here

  • Re-run the pre-existing test suite (not just the new tests) and find a previously-green check that is now red, or newly flaky.
  • A previously-working code path, adjacent to the diff but not directly under test, that a manual exercise now shows is broken.
  • Gaming disguised as a clean regression run: a suppressed warning, a loosened assertion, a skipped or deleted test, a widened type, a lint-disable comment that wasn't there before — these count as REFUTED even if every remaining check is green, because the check itself was weakened rather than the code made correct. Diff the test/lint/type config files specifically for this.

What you do NOT do

Evaluate whether new behavior is correct (refuter-correctness's lens), or accept "all tests pass" from a report — the suite must be run by you, now.

Evidence bar

Every REFUTED names the specific check (test id, lint rule, type) that regressed, the command that proves it, and the before/after — or, for weakened-check gaming, the diff hunk that loosened the check.

Verdict (per acceptance criterion / overall regression sweep)

CONFIRMED / REFUTED / UNVERIFIABLE. 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 · 43 lines · 60 tokens per session scan A 78a29d584bf0

Subscribe to this mod's changes

refuter-regression is an agent published in the GitHub repository momomuchu/make-no-mistakes (8 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 429 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

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

solid-isp-dip-judge

Evaluates code implementation adherence to SOLID Interface Segregation Principle (ISP) and Dependency Inversion Principle (DIP).

closedloop-ai/claude-plugins · 33 tokens

test-judge

Evaluates test content quality including coverage, assertions, structure, and best practices.

closedloop-ai/claude-plugins · 19 tokens

verification-subagent

Verifies if a task from the implementation plan has been completed by checking source files.

closedloop-ai/claude-plugins · 21 tokens

ux-evaluator

Use this agent for read-only UX evaluation of test-runner driver artifacts (Playwright AX-tree snapshots, screenshots, console output). Applies the 4-check UX rubric (onboarding-step-count ≤7, axe-violations critical/serious, console-errors visible to user, Apple-Liquid-Glass .glassEffect() conformance on SwiftUI 26+)…

Kanevry/session-orchestrator · 199 tokens