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 agentmods add skills/wittyreference/twilio-claude-plugin/adversarial-reviewnpx skills add wittyreference/twilio-claude-plugin --skill adversarial-reviewgit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWrote 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/wittyreference/twilio-claude-plugin/adversarial-review)<a href="https://agentmods.dev/skills/wittyreference/twilio-claude-plugin/adversarial-review"><img src="https://agentmods.dev/badge/skills/wittyreference/twilio-claude-plugin/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 | $0.00013 | $0.01661 |
| Opus 5 | $0.00006 | $0.00830 |
| Sonnet 5 | $0.00003 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
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 6d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: adversarial-review description: Four-phase adversarial review — initial expert assessment, isolated advocate + critic, objective arbiter synthesis. Use for technology adoption decisions, architectural changes, process changes, or any decision that benefits from structured debate.
Adversarial Review
A structured four-phase decision analysis for significant technical or strategic questions. Produces a balanced, evidence-based recommendation by having isolated agents argue opposing positions before an objective arbiter synthesizes.
When to Use
- Technology adoption decisions (new DB, framework, tool, service)
- Architectural changes with significant trade-offs
- Process or workflow changes affecting team productivity
- Any decision where confirmation bias is a risk
- When the question is "should we do X?" and X has meaningful costs and benefits
When NOT to Use
- Bug fixes, implementation details, naming conventions
- Decisions where one option is obviously correct
- Time-sensitive issues requiring immediate action
- Questions with insufficient data to meaningfully debate
Phase 1: Initial Assessment
Launch Explore agents (1-3 depending on scope) to gather facts:
- Codebase evidence: What exists today? What are the current pain points? What has been tried?
- External research: What does the literature say? What have peers done? What's the state of the art?
- Quantitative data: Sizes, counts, frequencies, costs, timelines — not vibes
Write the initial assessment to the plan file with these sections:
- Context: Why this question now, what prompted it
- Current State: How things work today, with measured data
- Research Findings: What external sources say, with citations
- Symptom Analysis: What's broken, what works, would the proposed change help each symptom?
- Cost-Benefit Analysis: Concrete benefits vs concrete costs, not aspirational vs abstract
- Technology Options: If adopting, what specific stack? If not, what alternatives?
- Preliminary Recommendation: Author's honest take, clearly labeled as preliminary
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.
- 6d ago First seen · 137 lines · 13 tokens per session scan A 633144a3901e
adversarial-review is a skill published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 1,661 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…