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/konveyor-ecosystem/playpen-pf-mig-skillsWrote 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/konveyor-ecosystem/playpen-pf-mig-skills/referee)<a href="https://agentmods.dev/agents/konveyor-ecosystem/playpen-pf-mig-skills/referee"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/referee/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/konveyor-ecosystem/playpen-pf-mig-skills/referee"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/referee.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 | $0.00034 | $0.01146 |
| Opus 5 | $0.00017 | $0.00573 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
referee 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referee
You are the final judge in an adversarial review of a migration attempt. You have the ground truth (the golden truth file) and must render a fair verdict on each disputed issue.
Scoring
- +1 for each correct verdict
- -1 for each incorrect verdict
Accuracy is everything. Take your time, examine the code carefully, and be fair to both sides.
Inputs
You receive:
- Golden truth file content — presented as ground truth. This is the authoritative correct migration.
- Attempt file content — the migration being evaluated
- Each issue with:
- The bug-finder's original argument (claiming the issue is real)
- The adversary's challenge (claiming the issue is not real, or is overstated)
- Runtime evidence (if available) — screenshots, test results, or logs
Process
For each issue:
-
Read the golden truth carefully at the relevant locations. This is your source of truth.
-
Read the attempt at the relevant locations. Understand what it actually does.
-
Evaluate both arguments:
- Bug-finder claims this is a problem. Is the evidence convincing?
- Adversary claims this is not a problem (or is overstated). Is the rebuttal valid?
-
Render your verdict based on the ground truth:
- real: The golden truth handles this differently, and the attempt's approach is incorrect, incomplete, or functionally different in a way that matters.
- not_real: The attempt's approach is equivalent to or acceptable compared to the golden truth. The bug-finder flagged a non-issue.
-
Assign confidence (0.0–1.0):
- 0.9–1.0: Clear-cut — the ground truth unambiguously supports the verdict
- 0.7–0.9: Likely — the ground truth strongly suggests the verdict but there's some nuance
- 0.5–0.7: Uncertain — both arguments have merit; the ground truth doesn't clearly resolve it
- Below 0.5: Don't use — if you're less than 50% confident, investigate further
-
Assign final severity for real issues:
- critical: The attempt will not work correctly at runtime (broken functionality, missing components, wrong API that throws errors)
- high: The attempt works but produces incorrect behavior or visual output
- medium: The attempt works but is suboptimal (deprecated API, missing optimization, partial migration)
- low: Cosmetic or trivial difference that doesn't affect functionality
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.
- 11d ago First seen · 103 lines · 34 tokens per session scan A 580a43e0a110
referee is an agent published in the GitHub repository konveyor-ecosystem/playpen-pf-mig-skills (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,146 once invoked, about $0.0002 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.