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 CassioRoos/godfly-skills --skill adversarial-reviewgit clone --depth 1 https://github.com/CassioRoos/godfly-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/skills/cassioroos/godfly-skills/adversarial-review)<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/adversarial-review"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/adversarial-review/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/cassioroos/godfly-skills/adversarial-review"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/adversarial-review.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 | $0.00186 | $0.02059 |
| Opus 5.5 | $0.00074 | $0.00824 |
| Sonnet 5.5 | $0.00037 | $0.00412 |
| Haiku 4.5 | $0.00019 | $0.00206 |
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 15d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Review
Find what breaks before production does. Investigate first, then challenge the work with evidence, then land on a verdict. The target is the artifact, never the people attached to it.
This skill is self-contained: everything it needs is in this file and in
references/. Load a reference only when its lens is in play.
Pick the Lens
| Situation / command | Lens | Read |
|---|---|---|
PR, branch, incident fix, payment or data-integrity change (*review) |
Review + PR gate | references/pr-incident-gate.md (non-skippable for PRs and incident fixes) |
Launch readiness, attack paths, "what defends this" (*redblue) |
Red team / blue team | references/red-blue.md |
Before starting risky work, "it failed, why?" (*premortem) |
Premortem | references/premortem.md |
A decision is about to be made, argue the other side (*devil) |
Devil's advocate | references/devils-advocate.md |
Choosing between approaches, "what else could we do" (*alternatives) |
Competing alternatives | references/alternatives.md |
Reliability, "how does this break", SPOFs (*fail) |
Failure modes | references/failure-modes.md |
"What are we taking for granted" (*assumptions) |
Assumptions | references/assumptions.md |
"What would guarantee failure" (*invert) |
Inversion | inline below |
With no command, pick the lens from the request. For high or critical stakes, run more than one lens silently (see Depth) and report only the conclusions.
Depth
| Stakes | What runs |
|---|---|
| Low (naming, style) | One-line note. No lens. |
| Medium (library, approach) | Assumptions plus one evidence-backed challenge |
| High (architecture, product direction) | Full protocol plus the most relevant lens |
| Critical (irreversible, money or data at risk) | Full protocol plus the PR gate, failure modes, premortem, and inversion. Blocks until addressed. |
What ships with it
11 files 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.
- references/alternatives-matrix.md 3.9 KB
- references/alternatives.md 3.8 KB
- references/assumptions.md 1.7 KB
- references/devils-advocate.md 4.0 KB
- references/failure-dependency-chain.md 3.4 KB
- references/failure-fmea.md 5.4 KB
- references/failure-known-patterns.md 5.0 KB
- references/failure-modes.md 7.1 KB
- references/pr-incident-gate.md 3.6 KB
- references/premortem.md 2.1 KB
- references/red-blue.md 1.9 KB
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.
- 15d ago First seen · 172 lines · 186 tokens per session scan A 9c7a9b9b39e8
adversarial-review is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session and 2,059 once invoked, about $0.0007 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 2026-10-23.
adversarial-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adversarial-reviewCassioRoos/godfly-skills | Skill | 1 | yesterday | MIT | A | 186 | Claude Code |
| challenge-resolveBorda/AI-Rig | Skill | 31 | yesterday | Apache-2.0 | A | 74 | Claude Code, Codex |
| code-remediateBorda/AI-Rig | Skill | 31 | yesterday | Apache-2.0 | A | 39 | Claude Code, Codex |
| auditoliver-kriska/claude-elixir-phoenix | Skill | 573 | yesterday | MIT | A | 35 | Claude Code |
| ai-slop-cleanervibeeval/vibecosystem | Skill | 539 | 2d ago | MIT | A | 50 | Claude Code, Codex |
| code-review-webrampstackco/claude-skills | Skill | 1.0k | 11d ago | MIT | A | 121 | Claude Code |
| java-code-reviewsivaprasadreddy/sivalabs-agent-skills | Skill | 194 | 7d ago | MIT | A | 64 | Claude Code |