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.
git clone --depth 1 https://github.com/TheLobbi/claudeWrote 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/commands/thelobbi/claude/chaos-test)<a href="https://agentmods.dev/commands/thelobbi/claude/chaos-test"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/chaos-test.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 | $0.00000 | $0.02852 |
| Opus 5 | $0.00000 | $0.01426 |
| Sonnet 5 | $0.00000 | $0.00570 |
| Haiku 4.5 | $0.00000 | $0.00285 |
Grade A, and why
chaos-test 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 7d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chaos Engineering & Resilience Testing
Comprehensive chaos engineering and resilience testing to validate system behavior under failure conditions, network partitions, resource exhaustion, and cascading failures.
Purpose
Systematically inject controlled failures into your system to discover weaknesses, validate fault tolerance mechanisms, test disaster recovery procedures, and build confidence in system resilience before failures happen in production.
Multi-Agent Coordination Strategy
Uses controlled chaos pattern where chaos agents inject failures while monitoring agents observe system behavior and recovery, coordinated to ensure safety and comprehensive coverage.
Chaos Testing Architecture
``` ┌──────────────────────────────────────────────────┐ │ Chaos Engineering Command │ │ (chaos-orchestrator) │ └────────────┬─────────────────────────────────────┘ │ ┌────────┼────────┬────────┬────────┐ ▼ ▼ ▼ ▼ ▼ Inject Monitor Validate Rollback Report ```
Execution Flow
Phase 1: Baseline & Steady State (0-15 mins)
- steady-state-validator - Define steady state metrics
- baseline-recorder - Record normal system behavior
- sla-monitor - Establish SLA/SLO baselines
- health-checker - Verify all systems healthy
Phase 2: Chaos Experiment Design (15-30 mins)
- chaos-architect - Design chaos experiments
- failure-catalog - Catalog potential failure modes
- hypothesis-generator - Generate testable hypotheses
- risk-assessor - Assess experiment risk levels
Phase 3: Infrastructure Chaos (30-60 mins)
- instance-terminator - Random instance termination
- network-partitioner - Network partition injection
- latency-injector - Network latency/jitter injection
- packet-loss-simulator - Packet loss simulation
- dns-chaos - DNS resolution failures
- disk-failure-simulator - Disk I/O failures
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.
- 7d ago First seen · 391 lines · 0 tokens per session scan A 9f4ec1f71df3
chaos-test is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,852 tokens. 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 commands, from other repositories
verify
Run repository verification using the verification-loop skill.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.
check-dev
Type-check a Z specification with fuzz.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.