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 KevinZai/commander --skill chaos-packgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/chaos-pack)<a href="https://agentmods.dev/skills/kevinzai/commander/chaos-pack"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/chaos-pack.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 | $0.00018 | $0.00516 |
| Opus 5 | $0.00009 | $0.00258 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
ccc-pro-chaos 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this pack will do
- Scaffold network partition simulation: DNS failure, TCP timeout, latency injection middleware
- Generate circuit breaker implementation (half-open state, threshold config, per-dependency)
- Add bulkhead pattern: thread-pool isolation per dependency, queue depth limits
- Scaffold retry-with-jitter: exponential backoff + full jitter (AWS best practice)
- Generate chaos test harness: controlled fault injection in test env, assertion on recovery
- Add dependency kill switch: feature-flag-gated dependency disablement for safe drills
- Scaffold graceful degradation paths: cached responses, stale-while-revalidate, stub data
- Generate load shedding middleware: request queuing, priority lanes, shed-at-threshold
- Add database failure simulation: connection pool exhaustion, query timeout, replica lag
- Scaffold external API failure handling: mocked failure responses for Stripe, Twilio, SendGrid
- Generate GameDay runbook templates: scenario → hypothesis → inject → observe → recover
- Add chaos engineering CI gate: resilience regression tests on every deploy
- Scaffold timeout budget propagation: context deadlines through async call chains
- Generate failure mode catalog per service: FMEA (failure mode and effects analysis) template
Why Pro-only
Chaos engineering patterns require both infrastructure access and deep understanding of failure modes specific to each architectural layer. Naive fault injection can cause cascading failures in test environments. The scaffolding here encodes production-safe patterns used by teams at Netflix, AWS, and Google — not theory.
Coming in v4.2
This skill is scaffolded. Full implementation ships in v4.2. Sign up at commanderplugin.com/pro to get notified and receive early access.
Tier check
This skill checks isPro() from commander/cowork-plugin/lib/license.js before running. If your license tier is starter, it surfaces an upgrade prompt and exits cleanly — no partial scaffolding, no silent failure.
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 · 48 lines · 18 tokens per session scan A 2d7c18ccb693
ccc-pro-chaos is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 516 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 2026-09-03.
Other skills, from other repositories
execute
Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.
tdd
Use before implementation when behavior can be verified by automated tests and regression coverage has clear value. For bugs with an unknown root cause, use systematic-debugging first, then return for red-green. Follow red-green-refactor—write a failing test first, add only enough code to pass it, then refactor. Do…
sync
Validate the active spec.yaml against the Ironclad schema and refresh the inventory. Rarely needed manually — cladcreatefeature already auto-syncs the inventory and clad check / clad done self-validate the spec, so do NOT run it as a reflexive pre-flight before those. Use it only after you have directly hand-edited a…
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
vc:scenario
Generate comprehensive edge cases and test scenarios by decomposing features across 12 dimensions. Use before implementation or testing to catch issues early.
api-mocking
API mock configuration for tests. Trigger when the user wants to mock APIs, use MSW, or test without a backend.