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 softspark/ai-toolkit --skill chaosgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/chaos)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/chaos"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/chaos/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/softspark/ai-toolkit/chaos"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/chaos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 43 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00031 | $0.00529 |
| Opus 5.5 | $0.00012 | $0.00212 |
| Sonnet 5.5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
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 1mo 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.
What it actually says
Chaos Command
$ARGUMENTS
Triggers a controlled resilience experiment.
Usage
/chaos <experiment> [target]
# Example: /chaos latency backend-api
# Example: /chaos kill redis
Protocol
- Safety Check: Verify env != PROD.
- Baseline: Check system health is green.
- Inject: Run the fault injection.
- Observe: Monitor logs/metrics for 60s.
- Recover: Restore system health.
- Report: Did we survive?
Rules
- MUST verify target environment is non-production before injecting
- NEVER run against a system without a healthy baseline
- CRITICAL: abort immediately if recovery does not complete within the observation window
- MANDATORY: log every injected fault with timestamp and scope
Gotchas
NODE_ENV=productionon a developer's machine is common — checking that env var alone is not enough proof of non-prod. Combine with kubeconfig context, cloud account ID, or a project-specific env file check before injecting.docker statsreports cached values; the first sample immediately after injection is often pre-fault. Wait at least 5 seconds before reading metrics.- Kubernetes liveness probes may self-heal the faulted pod inside the 60s observation window — the report shows green while the workload is still flapping. Check pod restart counters, not just health endpoints.
- Latency injected with
tc(Linux traffic control) persists across container restarts on the host and across SIGTERM. Always pair the inject step with an explicittc qdisc del dev <iface> rootcleanup in the recover step — theforkcontext will not undo it for you.
When NOT to Use
- In production without an explicit, written runbook — use
/workflow incident-responsefor real incidents - When the system has no observability (no metrics, no logs) — fix observability first
- For load testing — use dedicated load-test tooling, not chaos injection
- During an active incident — stabilize first with
/panic, then investigate
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.
- 1mo ago First seen · 54 lines · 31 tokens per session scan A 4896eb51bcd3
chaos is a skill published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 529 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.