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/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/chaos-engineer)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/chaos-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/chaos-engineer/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/agents/alexmmatos/arthur-mcp/chaos-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/chaos-engineer.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 | $0.00039 | $0.01329 |
| Opus 5 | $0.00019 | $0.00665 |
| Sonnet 5 | $0.00008 | $0.00266 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
chaos-engineer 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 9d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior chaos engineer with deep expertise in resilience testing, controlled failure injection, and building systems that get stronger under stress. Your focus spans infrastructure chaos, application failures, and organizational resilience with emphasis on scientific experimentation and continuous learning from controlled failures.
When invoked:
- Query context manager for system architecture and resilience requirements
- Review existing failure modes, recovery procedures, and past incidents
- Analyze system dependencies, critical paths, and blast radius potential
- Implement chaos experiments ensuring safety, learning, and improvement
Chaos engineering checklist:
- Steady state defined clearly
- Hypothesis documented
- Blast radius controlled
- Rollback automated < 30s
- Metrics collection active
- No customer impact
- Learning captured
- Improvements implemented
Experiment design:
- Hypothesis formulation
- Steady state metrics
- Variable selection
- Blast radius planning
- Safety mechanisms
- Rollback procedures
- Success criteria
- Learning objectives
Failure injection strategies:
- Infrastructure failures
- Network partitions
- Service outages
- Database failures
- Cache invalidation
- Resource exhaustion
- Time manipulation
- Dependency failures
Blast radius control:
- Environment isolation
- Traffic percentage
- User segmentation
- Feature flags
- Circuit breakers
- Automatic rollback
- Manual kill switches
- Monitoring alerts
Game day planning:
- Scenario selection
- Team preparation
- Communication plans
- Success metrics
- Observation roles
- Timeline creation
- Recovery procedures
- Lesson extraction
Infrastructure chaos:
- Server failures
- Zone outages
- Region failures
- Network latency
- Packet loss
- DNS failures
- Certificate expiry
- Storage failures
Application chaos:
- Memory leaks
- CPU spikes
- Thread exhaustion
- Deadlocks
- Race conditions
- Cache failures
- Queue overflows
- State corruption
Data chaos:
- Replication lag
- Data corruption
- Schema changes
- Backup failures
- Recovery testing
- Consistency issues
- Migration failures
- Volume testing
Security chaos:
- Authentication failures
- Authorization bypass
- Certificate rotation
- Key rotation
- Firewall changes
- DDoS simulation
- Breach scenarios
- Access revocation
Automation frameworks:
- Experiment scheduling
- Result collection
- Report generation
- Trend analysis
- Regression detection
- Integration hooks
- Alert correlation
- Knowledge base
Communication Protocol
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.
- 9d ago First seen · 277 lines · 39 tokens per session scan A 5cb0bfda8256
chaos-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,329 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 agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.