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/adilkalam/orca/adversarial-analysisnpx skills add adilkalam/orca --skill adversarial-analysisgit clone --depth 1 https://github.com/adilkalam/orcaWrote 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/adilkalam/orca/adversarial-analysis)<a href="https://agentmods.dev/skills/adilkalam/orca/adversarial-analysis"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/adversarial-analysis.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 | $0.00047 | $0.01826 |
| Opus 5 | $0.00023 | $0.00913 |
| Sonnet 5 | $0.00009 | $0.00365 |
| Haiku 4.5 | $0.00005 | $0.00183 |
Grade A, and why
adversarial-analysis 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 4d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Analysis
RULE: Before implementing any significant proposal, systematically attack it to find weaknesses.
The Principle
Proposals that survive adversarial scrutiny are more robust. This skill provides a 6-phase framework for stress-testing ideas before commitment.
Loading This Skill
Agents can load via:
required_skills:
- adversarial-analysis
Or dynamically invoke:
skill: adversarial-analysis
The 6-Phase Framework
Phase 1: Pre-mortem
"It's 6 months from now. This failed. Why?"
Assume complete failure and work backwards. What went wrong?
Process:
- Vividly imagine the failure state
- Identify 5-7 distinct failure scenarios
- Trace each back to root causes
- Note which causes were preventable
Output format:
### Pre-mortem
> "It's 6 months from now. This failed. Why?"
- [Failure scenario 1]: [Root cause]
- [Failure scenario 2]: [Root cause]
- [Failure scenario 3]: [Root cause]
Phase 2: Assumption Audit
Every proposal rests on assumptions. Surface and stress-test them.
Process:
- List every assumption (explicit and implicit)
- Rate confidence: H (high) / M (medium) / L (low)
- For each, answer: "If wrong, what breaks?"
Output format:
### Assumptions (confidence: H/M/L)
| Assumption | Confidence | If Wrong |
|------------|------------|----------|
| [Assumption 1] | M | [Impact if false] |
| [Assumption 2] | L | [Impact if false] |
| [Assumption 3] | H | [Impact if false] |
Prioritize low-confidence, high-impact assumptions for deeper analysis.
Phase 3: Edge Case Storm
Generate 10+ scenarios that could break the proposal.
Process:
- Think about boundary conditions
- Consider rare but possible inputs
- Imagine hostile actors
- Consider scale extremes (0, 1, many, millions)
- Consider timing/ordering issues
- Consider resource exhaustion
- Consider integration failures
Output format:
### Edge Cases
- [Breaking scenario 1]
- [Breaking scenario 2]
- [Breaking scenario 3]
... (minimum 10)
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.
- 4d ago First seen · 309 lines · 47 tokens per session scan A 0753ec6bea12
adversarial-analysis is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,826 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…