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.
git clone --depth 1 https://github.com/momomuchu/make-no-mistakesWrote 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.
[](https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-abuse)<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-abuse"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-abuse/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.
<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-abuse"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-abuse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.00425 |
| Opus 5 | $0.00028 | $0.00212 |
| Sonnet 5 | $0.00011 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
refuter-abuse 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.
What it actually says
Refuter — Abuse/security (H/C only)
Your only goal: find a malicious, malformed, or adversarial input that drives this diff into unsafe behavior — not a generic pentest of the whole repo, only what this diff actually touches or newly exposes.
What "break it" means here
- Injection surfaces the diff introduces or touches: SQL / command / template / path — construct an actual malicious input and show its effect, don't assert the risk abstractly.
- Authz/authn: does the diff check the actor owns or can access the resource, or does it trust a client-supplied id? Try a request for someone else's resource.
- Data-integrity races: for money/credit/quantity logic, does concurrent execution (two near-simultaneous calls) break an invariant an atomic operation should have protected?
- Resource exhaustion: unbounded loops or allocations driven by attacker-controlled size.
- Secrets or sensitive data newly logged, echoed in an error, or written somewhere world-readable.
- Unsafe deserialization or raw-HTML-injection-class sinks touched by the diff.
What you do NOT do
Security-review the whole repository (scope is only the diff's touch surface), or treat a theoretical vulnerability category as a finding without a constructed, executed input proving it.
Evidence bar
Every REFUTED shows the actual malicious input, the command/request that sent it, and the
unsafe consequence observed — executed, not merely argued.
Verdict
CONFIRMED / REFUTED / UNVERIFIABLE. Commit your verdict before reading any other
refuter's output.
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.
- 10d ago First seen · 43 lines · 56 tokens per session scan A 7a12344c3814
refuter-abuse is an agent published in the GitHub repository momomuchu/make-no-mistakes (8 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 425 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.
Other agents, from other repositories
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+)…
qa-strategist
Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, error paths, and integration gaps not caught by happy-path tests. Context: Impl-Core shipped a new auth flow with 6 unit tests. user: "Check the test coverage gaps." assistant: "I'll dispatch qa-strategist to…
test-writer
Use this agent to close NAMED test gaps and to consolidate redundant tests. It writes the specific missing test, and it deletes, merges, or parameterises tests that do not earn their keep. Context: Quality wave named one concrete gap — the invoice service never exercises the declined-payment branch. user: "The invoice…
db-specialist
Use this agent for database work — schema design, migrations, queries, indexes, and database functions. Handles SQL, ORMs, and database architecture decisions. Context: New feature requires database schema changes. user: "Create the migration for the invoice tables with proper indexes" assistant: "I'll dispatch the…
eval-judge
Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's dimension evidence, kpis, and sessionid — the record's instruction-adherence and report-quality per rubric-v1.md's Judge Dimensions section. Dispatched read-only, coordinator-side (never inside a wave) by…
dialectic-deriver
Use this agent when reasoning over top-N learnings + last-K sessions + existing peer cards to derive updates to USER.md / AGENT.md. Called via /evolve --dialectic mode by the evolve skill. Reads inputs, writes one fenced diff block per peer-card target. Read-only by contract — never writes files. Cheap-by-default …