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/proffesor-for-testing/agentic-qeWrote 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/proffesor-for-testing/agentic-qe/aqe-chaos)<a href="https://agentmods.dev/commands/proffesor-for-testing/agentic-qe/aqe-chaos"><img src="https://agentmods.dev/badge/commands/proffesor-for-testing/agentic-qe/aqe-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/commands/proffesor-for-testing/agentic-qe/aqe-chaos"><img src="https://agentmods.dev/badge/commands/proffesor-for-testing/agentic-qe/aqe-chaos.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 | $0.00016 | $0.02986 |
| Opus 5.5 | $0.00006 | $0.01194 |
| Sonnet 5.5 | $0.00003 | $0.00597 |
| Haiku 4.5 | $0.00002 | $0.00299 |
Grade A, and why
aqe-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 16d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AQE Chaos Testing
Run chaos testing scenarios to validate system resilience and fault tolerance.
Usage
aqe chaos <scenario> [options]
# or
/aqe-chaos <scenario> [options]
Options
| Option | Type | Default | Description |
|---|---|---|---|
scenario |
string | required | Chaos scenario: latency, failure, resource-exhaustion, network-partition |
--duration |
number | 60 |
Test duration in seconds |
--intensity |
string | medium |
Intensity: low, medium, high, extreme |
--target |
string | all |
Target services/components |
--recovery-check |
boolean | true |
Verify system recovery after chaos |
--baseline |
path | - | Baseline metrics for comparison |
--abort-on-critical |
boolean | true |
Abort if critical failure detected |
Examples
Simulate Latency
aqe chaos latency --duration 60 --intensity medium
Injects network latency for 60 seconds at medium intensity.
Test Failure Scenarios
aqe chaos failure --target api-gateway --duration 120
Simulates API gateway failures for 2 minutes.
Resource Exhaustion
aqe chaos resource-exhaustion --intensity high --recovery-check
Tests system behavior under high resource pressure with recovery validation.
Network Partition
aqe chaos network-partition --duration 180 --target database
Simulates network partition between application and database for 3 minutes.
Combined Chaos
aqe chaos latency --intensity low --target api &
aqe chaos failure --intensity low --target database &
wait
Runs multiple chaos scenarios simultaneously.
Integration with Claude Code
Spawning Chaos Testing Agent
// Use Claude Code's Task tool to spawn the chaos testing agent
Task("Execute chaos testing scenario", `
Run comprehensive chaos testing:
- Scenario: Network latency + occasional failures
- Duration: 5 minutes
- Intensity: Medium
- Monitor: Response times, error rates, recovery time
Verify system resilience and document failure modes.
Store results in memory: aqe/chaos/{chaos-id}
`, "qe-test-executor")
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.
- 16d ago First seen · 443 lines · 16 tokens per session scan A a486f18502c8
aqe-chaos is a command published in the GitHub repository proffesor-for-testing/agentic-qe (515 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 2,986 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 2026-10-11.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.