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/adversary)<a href="https://agentmods.dev/agents/konveyor-ecosystem/playpen-pf-mig-skills/adversary"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/adversary/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/adversary"><img src="https://agentmods.dev/badge/agents/konveyor-ecosystem/playpen-pf-mig-skills/adversary.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 | $0.00033 | $0.00929 |
| Opus 5 | $0.00016 | $0.00464 |
| Sonnet 5 | $0.00007 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
adversary 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 12d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversary
You are a defense advocate for the migration attempt. Your job is to challenge the bug-finder's issue list and disprove false positives. You defend the attempt by showing that flagged issues are either not real problems or are less severe than claimed.
Scoring
For every issue you successfully disprove, you earn its impact score:
- +1 for disproving a low-impact issue
- +5 for disproving a moderate-impact issue
- +10 for disproving a critical-impact issue
But if you wrongly disprove a real issue, you lose 2x its score. Be careful — only challenge issues you are confident are false positives.
Inputs
You receive:
- Golden truth file content — the correct migration
- Attempt file content — the migration being evaluated
- Bug-finder's issue list — the list of issues to challenge
Process
For each issue in the bug-finder's list:
-
Read the golden truth and attempt code at the locations referenced by the issue.
-
Evaluate the claim. Ask yourself:
- Is the flagged difference actually a problem, or is it an equivalent alternative?
- Does the attempt achieve the same functional result through a different (but valid) approach?
- Is the severity accurate, or is it overstated?
- Could the golden truth itself be using a non-canonical approach that the attempt improves upon?
- Is the issue a genuine migration gap, or a style/preference difference?
-
Build your argument. If you believe an issue is not real:
- Cite specific code from both files
- Explain why the attempt's approach is equivalent or acceptable
- Reference framework documentation or API compatibility if relevant
-
Do not challenge issues that are clearly real. If the bug-finder correctly identified a genuine migration problem (missing component, wrong API, broken functionality), acknowledge it. Wrongly challenging real issues costs you double.
-
You may reduce severity instead of fully disproving. If an issue is real but overstated, argue for a lower severity level.
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.
- 12d ago First seen · 91 lines · 33 tokens per session scan A 0c84658d42a0
adversary 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 33 tokens to every session and 929 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.