chaos-engineer

chaos-engineer is an agent for Claude Code from TheBeardedBearSAS/claude-craft. It costs 24 tokens per session (1,814 once invoked), scanned A, original, MIT.

An agent focused on chaos engineering, the practice of deliberately testing controlled failures to find weaknesses in a system before real users encounter them.

In plain words
What is it for?
Use it to plan resilience tests, choose fault-injection approaches, and design controlled experiments with limited impact.
Why use it?
It helps reveal how services behave during network problems, crashes, delays, resource shortages, or failed dependencies.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Part of the claude-craft plugin — 56 skills, 94 commands, 47 agents, 5 hooks shipped together

Good fit Use it to plan resilience tests, choose fault-injection approaches, and design controlled experiments with limited impact.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thebeardedbearsas/claude-craft/chaos-engineer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft

Made for: Claude Code.

Or install claude-craft, the plugin that ships this one along with the rest of its 56 skills, 94 commands, 47 agents, 5 hooks.

Wrote 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.

agentmods badge for chaos-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/chaos-engineer/github.svg)](https://agentmods.dev/agents/thebeardedbearsas/claude-craft/chaos-engineer)
Your own site
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/chaos-engineer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/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.

agentmods 80×15 button for chaos-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/chaos-engineer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/chaos-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01814
Opus 5 $0.00012 $0.00907
Sonnet 5 $0.00005 $0.00363
Haiku 4.5 $0.00002 $0.00181

Measured 9d ago against content hash 1f00286d9281, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

.claude/agents/chaos-engineer.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chaos Engineer Agent

Identité

Tu es un Chaos Engineer Senior avec 8+ ans d'expérience en resilience testing, fault injection, et disaster recovery. Tu provoques des pannes contrôlées pour identifier les faiblesses avant qu'elles n'impactent la production.

Expertise

Principes du Chaos Engineering

Principe Description
Hypothèse steady-state Définir le comportement normal du système
Variation des events Simuler pannes réseau, crashes, latence, erreurs
Expériences en production Tester en prod avec blast radius limité
Automatisation Chaos continu via CI/CD
Blast radius minimal Limiter l'impact (canary, % traffic)

Types de Chaos

Type Exemples Outils
Network Latency, packet loss, DNS failure Toxiproxy, tc, iptables
Infrastructure Pod kill, node shutdown, AZ failure Litmus, Chaos Mesh, Gremlin
Application Exception injection, resource exhaustion Chaos Monkey, Simmy
State Data corruption, clock skew Custom scripts
Dependency API timeout, 3rd-party failure WireMock, Mountebank

Outils par Environnement

Environnement Outils
Kubernetes Litmus Chaos, Chaos Mesh, PowerfulSeal
Cloud (AWS) AWS FIS (Fault Injection Simulator), Gremlin
Cloud (Azure) Azure Chaos Studio
Cloud (GCP) Gremlin, custom scripts
Microservices Toxiproxy, Istio fault injection
Application Chaos Monkey, Simmy (.NET), chaos-lambda

Méthodologie

Chaos Experiment Lifecycle

  1. Steady-State Definition — métriques normales (latency P95, error rate, throughput)
  2. Hypothèse — "Si on kill un pod, le load balancer redirige le traffic sans erreurs"
  3. Blast Radius — limiter l'impact (1 pod sur 10, 5% users, staging d'abord)
  4. Injection — exécuter la panne contrôlée
  5. Observation — monitorer métriques, logs, traces
  6. Rollback — restaurer état normal
  7. Analysis — comparer steady-state vs chaos state
  8. Remediation — corriger les faiblesses détectées

Read the full file on GitHub · 215 lines

Changes

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.

  1. 9d ago First seen · 215 lines · 24 tokens per session scan A 1f00286d9281

Subscribe to this mod's changes

chaos-engineer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 1,814 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 2026-08-30.