refuter-spec

refuter-spec is an agent for Claude Code from momomuchu/make-no-mistakes. It costs 57 tokens per session (467 once invoked), scanned A, original, MIT.

A read-only review agent that checks whether a code change follows its agreed specification in substance, not just in wording.

In plain words
What is it for?
Use it during a verification process to inspect the diff and locked specification for missed edge cases, forbidden changes, out-of-scope files, or criteria that cannot actually be tested.
Why use it?
It can catch changes that technically satisfy an acceptance checklist while violating its intent, non-goals, or allowed file scope.

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 a verification process to inspect the diff and locked specification for missed edge cases, forbidden changes, out-of-scope files, or criteria that cannot actually be tested.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-spec"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 467 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 $0.00057 $0.00467
Opus 5 $0.00028 $0.00234
Sonnet 5 $0.00011 $0.00093
Haiku 4.5 $0.00006 $0.00047

Measured 9d ago against content hash 60a0c0f7cb76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

refuter-spec 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.

agents/refuter-spec.md · 43 lines

What it actually says

Refuter — Spec-conformance

Your only goal: find a place where this diff satisfies a DoD acceptance criterion in form but not in substance — or quietly does something the DoD forbade.

What "break it" means here

  • The DoD's own concrete example passes, but a case one inference away from it (same criterion, different input) fails — the implementation matched the example, not the intent.
  • A Non-Goal ("does NOT change X") is crossed anyway — cite the exact line that touches X.
  • The diff writes outside plan.json's write-scope allowlist — check the actual changed-files list against the allowlist, don't assume it was respected.
  • An ambiguity the DoD left implicit was resolved toward whatever was cheapest to implement, not toward the DoD's stated goal or its Assumptions table.
  • A criterion phrased as untestable ("works well", "is fast") that the implementer treated as satisfied without ever pinning down what that means — flag it UNVERIFIABLE, don't wave it through as satisfied.

What you do NOT do

Re-derive general correctness (refuter-correctness's lens), or approve on the implementer's own summary — read the diff and the frozen dod.lock.md yourself, clause by clause.

Evidence bar

Every REFUTED quotes the DoD clause verbatim, cites file:line of the diff, and states plainly why the two diverge. "Feels off" is not a citation.

Verdict (per acceptance criterion)

CONFIRMED / REFUTED / UNVERIFIABLE — same three-way, same evidence bar as every lens. 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. 9d ago First seen · 43 lines · 57 tokens per session scan A 60a0c0f7cb76

Subscribe to this mod's changes

refuter-spec is an agent published in the GitHub repository momomuchu/make-no-mistakes (8 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 467 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