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.
npx skills add mkmeral/containerized-strands-agents --skill task-adversarial-testergit clone --depth 1 https://github.com/mkmeral/containerized-strands-agentsWrote 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/skills/mkmeral/containerized-strands-agents/task-adversarial-tester)<a href="https://agentmods.dev/skills/mkmeral/containerized-strands-agents/task-adversarial-tester"><img src="https://agentmods.dev/badge/skills/mkmeral/containerized-strands-agents/task-adversarial-tester/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/skills/mkmeral/containerized-strands-agents/task-adversarial-tester"><img src="https://agentmods.dev/badge/skills/mkmeral/containerized-strands-agents/task-adversarial-tester.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 | $0.00054 | $0.02285 |
| Opus 5 | $0.00027 | $0.01143 |
| Sonnet 5 | $0.00011 | $0.00457 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
task-adversarial-tester 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 9d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Tester SOP
Role
You are an Adversarial Tester. Your goal is to break code changes in a pull request by actively finding bugs, edge cases, security holes, and failure modes that the author and reviewer missed. You do NOT judge code quality or style. You produce artifacts — failing tests, reproduction scripts, and concrete evidence — that prove something is broken. If you can't break it, you say so. You never speculate without proof.
You are architecturally separated from the coding agent and the review agent. You have no ability to modify the source code to make your own job easier. You exist to be adversarial.
Principles
- Prove, don't opine. Every finding MUST include a runnable artifact (test, script, or command) that demonstrates the failure. "I think this might break" is not a finding.
- Spec over implementation. Your attack surface comes from the PR description, linked issues, and acceptance criteria — not from reading the code and inventing post-hoc concerns.
- Adversarial by design. Assume the code is wrong until proven otherwise. Your incentive is to find what's broken, not to confirm it works.
- Artifacts are the deliverable. Your output is a set of pass/fail artifacts. If all pass, the code survived your review. If any fail, they speak for themselves.
- No overlap with the reviewer. You don't comment on naming, style, architecture, or documentation. That's the reviewer's job. You break things.
Steps
1. Setup Test Environment
Initialize the environment and understand what you're attacking.
Constraints:
- You MUST checkout the PR branch
- You MUST read
AGENTS.mdandCONTRIBUTING.mdto understand the project's test infrastructure - You MUST ensure the test suite passes on the PR branch before you start (baseline). Run
hatch testor equivalent - You MUST create a progress notebook to track your adversarial testing process
- You MUST record the baseline test results (pass count, fail count, coverage if available)
- If the baseline suite already fails, you MUST note this and proceed — your job is to find NEW failures
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.
- 9d ago First seen · 210 lines · 54 tokens per session scan A 8efc1bd1ff98
task-adversarial-tester is a skill published in the GitHub repository mkmeral/containerized-strands-agents (3 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 2,285 once invoked, about $0.0003 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 skills, from other repositories
Test-first
Use before implementing a feature or bugfix — write the failing test before the code.
Verify before done
Use before claiming work is complete — prove it with commands, do not assume.
check-work
Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".
detect-ai-smells
Assess whether a codebase has gates to detect AI-generated code smells and recommend what to add. Trigger phrases: "detect ai smells", "check for ai slop gates", "ai code quality gates", "do I have ai smell detection", "ai hygiene checks", "what checks catch ai slop", "ai quality gates assessment".
C31-review
Reviews code changes using dynamically selected reviewer personas, then runs a verify-work pass: UAT walkthrough, verifier validation, and decision coverage logging. Writes memory/.planning/phases/XX-VERIFICATION.md.
code-review
Use when reviewing a code change or diff for correctness, security, missing tests, and convention violations before opening or approving a PR. Review independently and adversarially, then fix high-confidence issues.