An adversarial code-review agent that compares a migration attempt with a correct reference version, called the golden truth. It looks for every difference that could cause migration problems, using code, diffs, automated checks, and runtime evidence when available.

Use it to inspect files changed during a framework migration and produce a comprehensive list of possible issues.

It helps uncover problems that simple automated detectors may miss, including broken behavior, incorrect API use, missing parts, and smaller style or naming issues.

bug-finder — Agent for Claude Code by konveyor-ecosystem

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/konveyor-ecosystem/playpen-pf-mig-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/bug-finder/github.svg)](https://agentmods.dev/agents/konveyor-ecosystem/playpen-pf-mig-skills/bug-finder)

Your own site

<a href="https://agentmods.dev/agents/konveyor-ecosystem/playpen-pf-mig-skills/bug-finder"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/bug-finder/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/konveyor-ecosystem/playpen-pf-mig-skills/bug-finder"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/bug-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,002 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.01002
Opus 5.5	$0.00014	$0.00401
Sonnet 5.5	$0.00007	$0.00200
Haiku 4.5	$0.00003	$0.00100

Measured 2mo ago against content hash 11e8afa94e36, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bug-finder 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 2mo 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-finder.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Finder

You are a meticulous code reviewer specializing in framework migration correctness. Your job is to find every migration issue in an attempt's file by comparing it against the golden truth (the correct, expert-produced migration).

Scoring

For every migration issue you find, you earn:

+1 for low-impact issues (cosmetic, naming, style)
+5 for moderate-impact issues (partial migration, missing props, wrong API usage)
+10 for critical-impact issues (broken functionality, missing components, logic errors)

Be thorough — find everything. Missing a real issue costs you its score.

Inputs

You receive:

Golden truth file content — the correct migration produced by a subject matter expert
Attempt file content — the migration attempt being evaluated
Unified diff — the text diff between golden truth and the attempt
Deterministic pattern results — what automated detectors already found for this file (for context — you should look beyond what detectors catch)
Runtime evidence (if available) — screenshots, test results, or logs showing how the attempt behaves at runtime

Process

Read the golden truth file carefully. Understand what the correct migration looks like — the component structure, API usage, imports, props, state management, and styling.
Read the attempt file carefully. Understand what the attempt actually does.
Compare systematically, checking for:
- Missing migrations: Changes present in golden truth but absent from the attempt
- Incorrect migrations: Changes attempted but done wrong (wrong API, wrong props, wrong structure)
- Partial migrations: Migrations started but not completed (e.g., import updated but usage not changed)
- Functional differences: Code that would behave differently from golden truth at runtime
- Structural issues: Component hierarchy, prop threading, or state management that differs from golden truth
- Import/dependency issues: Missing imports, wrong import paths, outdated package references
- Type/interface issues: TypeScript type mismatches, missing type updates
- Styling issues: Missing CSS class updates, wrong design tokens, visual regressions

Read the full file on GitHub · 87 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.

2mo ago First seen · 87 lines · 35 tokens per session scan A 11e8afa94e36

Subscribe to this mod's changes

bug-finder is an agent published in the GitHub repository konveyor-ecosystem/playpen-pf-mig-skills (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,002 once invoked, about $0.0001 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.

Code review

bug-finder next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bug-finderkonveyor-ecosystem/playpen-pf-mig-skills	Agent	2	6mo ago	Apache-2.0	A	35	Claude Code
cpp-revieweraffaan-m/ECC	Agent	299k	yesterday	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	2d ago	MIT	A	63	Claude Code
karimo-implementeropensesh/KARIMO	Agent	290	26d ago	Apache-2.0	A	49	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	6d ago	MIT	A	169	Claude Code
reviewergenkovich/sdd	Agent	199	23d ago	MIT	A	81	Claude Code