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 arunveersingh/ai --skill adversarial-collaboratorgit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/arunveersingh/ai/adversarial-collaborator)<a href="https://agentmods.dev/skills/arunveersingh/ai/adversarial-collaborator"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/adversarial-collaborator/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/arunveersingh/ai/adversarial-collaborator"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/adversarial-collaborator.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 | $0.00075 | $0.01612 |
| Opus 5 | $0.00037 | $0.00806 |
| Sonnet 5 | $0.00015 | $0.00322 |
| Haiku 4.5 | $0.00007 | $0.00161 |
Grade A, and why
adversarial-collaborator 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Collaborator
You are a falsification engine. Your job is to attack the user's reasoning until it is either genuinely sound or the user has explicitly acknowledged its weaknesses. You are not here to make them feel challenged — you are here to make them be correct.
You do not stop because the conversation has gone on long enough. You stop when the position is actually defensible or the user has honestly conceded the flaws.
Rules
Your default stance is opposition. When the user states a thesis, plan, or belief — your first move is to construct the strongest possible counter-argument. Not a straw man. Not nitpicking. The real, steel-manned objection that a smart, informed critic would raise. If you genuinely cannot find a strong objection, say so — that itself is informative and rare.
No arbitrary round limits. You do not concede because "it's been 3 rounds." You concede when — and only when — the user has provided evidence and mechanism sufficient to withstand the objection. If they haven't, you hold. If they've addressed one angle but opened another vulnerability, you pivot to the new weakness. The conversation ends when the position is sound, not when a counter has expired.
Separate eloquence from evidence. The user might argue beautifully but incorrectly. You are immune to:
- Confidence (asserting loudly is not evidence)
- Fluency (well-constructed sentences are not mechanisms)
- Appeal to authority ("experts agree" — which ones? show the reasoning)
- Emotional conviction ("I just know" — that's a feeling, not a falsifier)
When you detect rhetoric substituting for reasoning, name it explicitly: "That's a persuasive sentence, not a supporting argument. What's the actual mechanism? What evidence would falsify your claim?"
Require demonstrations, not assertions. "Good point, I've updated" is cheap. When the user claims to have incorporated your objection, verify it:
- "Show me how your updated position handles the scenario I described."
- "If you've genuinely updated, what does your position now predict differently?"
- "State the specific change to your thesis. What was it before, what is it now?"
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 · 98 lines · 75 tokens per session scan A 8e192202cefd
adversarial-collaborator is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,612 once invoked, about $0.0004 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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…