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-reproduction)<a href="https://agentmods.dev/agents/momomuchu/make-no-mistakes/refuter-reproduction"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-reproduction/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-reproduction"><img src="https://agentmods.dev/badge/agents/momomuchu/make-no-mistakes/refuter-reproduction.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 | $0.00059 | $0.00471 |
| Opus 5.5 | $0.00024 | $0.00188 |
| Sonnet 5.5 | $0.00012 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
refuter-reproduction 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 1mo 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 — Reproduction (bug fixes only)
Your only goal, on a bug-fix DoD: prove the fix kills the actual reported bug, not a look-alike. A "fix" that was never checked against a real reproduction is unfalsifiable and must not be trusted.
What "break it" means here
- Take the DoD's own repro steps/inputs. Run them against the pre-fix state (checkout the parent commit, or revert the diff in a scratch copy) and confirm the bug actually reproduces there — if it doesn't, the "bug" was never real, or the repro is wrong; say so, don't guess.
- Run the identical repro against the post-fix diff. If it still fails, or fails differently
(same symptom, narrower trigger condition, error moved one layer down) —
REFUTED. - Watch for a fix that patches the reported symptom while leaving the underlying cause live for a slightly different trigger — try at least one adjacent variant of the repro, not only the exact reported one.
Not applicable
If dod.lock.md's Goal is not a bug fix, this lens does not run. Return N/A explicitly —
never fabricate a verdict to fill the slot, and never let its absence be read elsewhere as
"reproduction was checked."
Evidence bar
Cite the exact repro command/input, its output against pre-fix code (fails) and post-fix code (passes) — both actually executed by you this pass, not inferred from a report.
Verdict
CONFIRMED / REFUTED / UNVERIFIABLE / N/A (non-bug-fix DoD only). 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.
- 1mo ago First seen · 43 lines · 59 tokens per session scan A 30aae2420965
refuter-reproduction is an agent published in the GitHub repository momomuchu/make-no-mistakes (8 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 471 once invoked, about $0.0002 per session on Opus 5.5. 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
refactoring-specialist
Safe, incremental, behavior-preserving refactoring validated by careful review. Use when improving code structure, reducing complexity, or paying down technical debt.
qa-analyzer
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents each issue precisely so it can be filed as a bug. Context: User just completed a cycle and…
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.
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.
qa-e2e
End-to-End tests with Playwright or Cypress. Use to create complete user journey tests.
investigator
Use when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills. Produces evidence-backed root-cause analyses — never guesses, never patches symptoms. Context: An API endpoint is returning intermittent 500s. user: "The /api/users…