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 gabonio/agent-operator-toolkit --skill adversarial-reviewgit clone --depth 1 https://github.com/gabonio/agent-operator-toolkitWrote 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/gabonio/agent-operator-toolkit/adversarial-review)<a href="https://agentmods.dev/skills/gabonio/agent-operator-toolkit/adversarial-review"><img src="https://agentmods.dev/badge/skills/gabonio/agent-operator-toolkit/adversarial-review.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00328 |
| Opus 5 | $0.00034 | $0.00164 |
| Sonnet 5 | $0.00014 | $0.00066 |
| Haiku 4.5 | $0.00007 | $0.00033 |
Grade A, and why
adversarial-review 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 7d 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.
What it actually says
Adversarial Review
Read the adversarial lens, lens routing, and only the domain lenses relevant to the target.
Procedure
- Identify the artifact, approved objective, relevant constraints, and evidence available.
- State the review boundary and whether this is a same-context pass, fresh-context pass, automated evidence, or human review. Do not imply independence that did not occur.
- Challenge material assumptions, decision tradeoffs, failure modes, scale, trust boundaries, operability, and verification gaps.
- Verify claims against repository evidence where possible. Label observation, inference, hypothesis, and unanswered question distinctly.
- Report the three or four most material findings by default. Report fewer when fewer are real; do not fill the batch with style preferences or speculative criticism. For code, anchor each finding to the tightest useful path and line range.
- Include overlooked strengths, residual risks, and one verdict:
ready,ready with accepted risks,revise, orblocked on decision.
Remain read-only unless the user separately authorizes changes. A finding does not overrule repository evidence or user authority; document accepted risks clearly.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 20 lines · 68 tokens per session scan A decae18b6cd4
adversarial-review is a skill published in the GitHub repository gabonio/agent-operator-toolkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 328 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.