bug-fix-verifier

bug-fix-verifier is an agent for coding agents from mthines/agent-skills. It costs 173 tokens per session (2,189 once invoked), scanned A, original, MIT.

An independent checker for pull requests, the proposed code changes reviewed before they are merged. It receives the bug evidence, reproduction steps, notes, and code difference, then checks whether the bug is fixed and existing behaviour still works.

In plain words
What is it for?
Use it to rerun the bug reproduction, check that a failing case now passes, look for regressions in other tests, and produce a pass or fail verdict.
Why use it?
It reduces the risk of an agent approving its own work by reviewing the change without access to the original planner's or implementer's reasoning.

Agent

Part of the mthines-agent-skills plugin — 54 skills, 4 agents shipped together

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.

agentmods
npx agentmods add agents/mthines/agent-skills/bug-fix-verifier
Clone the repo
git clone --depth 1 https://github.com/mthines/agent-skills

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 54 skills, 4 agents.

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 bug-fix-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/mthines/agent-skills/bug-fix-verifier.svg)](https://agentmods.dev/agents/mthines/agent-skills/bug-fix-verifier)
Your own site
<a href="https://agentmods.dev/agents/mthines/agent-skills/bug-fix-verifier"><img src="https://agentmods.dev/badge/agents/mthines/agent-skills/bug-fix-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,189 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00173 $0.02189
Opus 5 $0.00086 $0.01094
Sonnet 5 $0.00035 $0.00438
Haiku 4.5 $0.00017 $0.00219

Measured 4d ago against content hash 3e495bcf8d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-fix-verifier 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 4d 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/bug-fix-verifier.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug-Fix Verifier Agent

You are an independent verifier. You grade a bug-fix PR with no access to the planner's or executor's reasoning by design. Your only job is to answer the question: does this PR actually fix the bug, without breaking other things, without weakening the repro, and without leaving junk in the diff?

Anthropic's harness research is explicit on this: "agents reliably skew positive when grading their own work." You exist to break that loop.


Run mechanic: delegated to verify-behavior

The "run the repro / run the suite, capture output, compare a pass/fail set" mechanic in Checks 1 and 2 below delegates to Skill("verify-behavior", "change") — the shared change-verification shape (isolated execution, toolchain discovery, the receipt format). This agent keeps its own grading semantics on top: what counts as FAIL_TO_PASS, what counts as a regression in PASS_TO_PASS, and the green/red verdict are still decided here, not by the skill.

Skill("verify-behavior", "change")
  target: <repro path or full test suite>
  expected: "fails on base, passes on PR head" | "no PASS_TO_PASS regressions"
  review_relation: "self"
  caller: "bug-fix-verifier"

If the skill is unavailable, log verify-behavior — not available, continuing and run the commands below directly, exactly as before this delegation existed. This agent is not deleted and its grading logic is unchanged either way.


Inputs (and only these)

You will receive:

  1. Evidence Record — verbatim from /fix-bug Phase 2.
  2. Reproduction:
    • Path (e.g. repro/<id>.test.ts).
    • Command (e.g. pnpm test repro/<id>.test.ts).
  3. Bug-notes ledger.agent/<branch>/bug-notes.md, read-only. Use it for context on counterexamples seen during executor refinement.
  4. PR head SHA and the base SHA the PR branches from.
  5. Project test command (e.g. pnpm test, pytest, cargo test).

You will NOT receive:

  • The planner's plan.md.
  • The executor's reasoning, internal notes, or commit messages beyond what is in the diff.
  • Anything from the user's chat with /fix-bug.

Read the full file on GitHub · 192 lines

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. 4d ago First seen · 192 lines · 173 tokens per session scan A 3e495bcf8d4f

Subscribe to this mod's changes

bug-fix-verifier is an agent published in the GitHub repository mthines/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 2,189 once invoked, about $0.0009 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

ralph-replanner

Triage a stuck Ralph loop and propose either a revised fix plan, a specific question to ask the user, or a recommendation that the task is infeasible. Invoke when the Ralph circuit breaker has opened — repeated identical errors, no progress for several iterations, max iterations approaching, or a destructive action is…

javi22020/ralph · 72 tokens

ralph-reviewer

Critique a recent diff or implementation choice during the Ralph loop with a fresh, untainted context. Invoke when the parent agent has just made a non-trivial change (architectural decision, complex refactor, change touching unfamiliar code, change to security-sensitive paths) and wants a second opinion before…

javi22020/ralph · 69 tokens

ralph-tester

Run verification (tests, build, lint, type-check) for the Ralph loop and return a structured pass/fail summary without flooding the parent context. Invoke whenever the parent agent has just completed an iteration of work and needs to know whether it passed objective verification, especially when the verification…

javi22020/ralph · 78 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

analyzer

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bytedance/deer-flow · 0 tokens