What is chaos-experiment?

A workflow for creating, running, and monitoring chaos experiments in Harness Chaos Engineering. Chaos experiments deliberately disrupt systems, such as deleting a pod, stressing CPU, or causing network faults.

Use it to check Harness infrastructure, browse experiment templates, create experiments, run them, and review their results.

It helps test whether a system stays reliable when parts fail, instead of discovering these weaknesses during a real outage.

chaos-experiment — Skill for Claude Code and Codex by harness

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.

Any agent

npx skills add harness/harness-ai --skill chaos-experiment

Clone the repo

git clone --depth 1 https://github.com/harness/harness-ai

Made for: Claude Code, Codex.

Or install harness, the plugin that ships this one along with the rest of its 55 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/harness/harness-ai/chaos-experiment/github.svg)](https://agentmods.dev/skills/harness/harness-ai/chaos-experiment)

Your own site

<a href="https://agentmods.dev/skills/harness/harness-ai/chaos-experiment"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/chaos-experiment/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/harness/harness-ai/chaos-experiment"><img src="https://agentmods.dev/badge/skills/harness/harness-ai/chaos-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 911 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00911
Opus 5	$0.00031	$0.00456
Sonnet 5	$0.00012	$0.00182
Haiku 4.5	$0.00006	$0.00091

Measured 11d ago against content hash 21a475e0b50b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

chaos-experiment 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 11d 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.

Origin

This is a copy

100% identical to chaos-experiment — 163 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/claude/skills/chaos-experiment/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chaos Experiment

Create and manage chaos experiments using Harness Chaos Engineering via MCP.

Instructions

Step 1: Check Infrastructure

Call MCP tool: harness_list
Parameters:
  resource_type: "chaos_infrastructure"
  org_id: "<organization>"
  project_id: "<project>"

Step 2: Browse Templates

Call MCP tool: harness_list
Parameters:
  resource_type: "chaos_experiment_template"
  org_id: "<organization>"
  project_id: "<project>"

Step 3: List Existing Experiments

Call MCP tool: harness_list
Parameters:
  resource_type: "chaos_experiment"
  org_id: "<organization>"
  project_id: "<project>"

Step 4: Create Experiment

Call MCP tool: harness_create
Parameters:
  resource_type: "chaos_experiment"
  org_id: "<organization>"
  project_id: "<project>"
  body: <experiment definition>

Step 5: Run Experiment

Call MCP tool: harness_execute
Parameters:
  resource_type: "chaos_experiment"
  action: "run"
  resource_id: "<experiment_id>"
  org_id: "<organization>"
  project_id: "<project>"

Step 6: Monitor Results

Call MCP tool: harness_list
Parameters:
  resource_type: "chaos_experiment_run"
  org_id: "<organization>"
  project_id: "<project>"

Get specific run details:

Call MCP tool: harness_get
Parameters:
  resource_type: "chaos_experiment_run"
  resource_id: "<run_id>"

Step 7: Check Probes

Call MCP tool: harness_list
Parameters:
  resource_type: "chaos_probe"
  org_id: "<organization>"
  project_id: "<project>"

Common Experiment Types

Pod Delete - Kill pods to test recovery
Pod CPU Hog - Stress CPU to test throttling
Pod Memory Hog - Consume memory to test OOM handling
Pod Network Loss - Simulate network failures
Pod Network Latency - Add artificial latency
Node Drain - Drain K8s nodes
EC2 Stop - Stop AWS EC2 instances
ECS Task Stop - Stop ECS tasks

Chaos Resource Types

Resource Type	Operations	Description
`chaos_experiment`	list, get, create, update, delete, run	Experiments
`chaos_experiment_run`	list, get	Run history/results
`chaos_experiment_template`	list, get	Pre-built templates
`chaos_infrastructure`	list, get	Target infrastructure
`chaos_probe`	list, get	Health probes

Read the full file on GitHub · 145 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.

11d ago First seen · 145 lines · 62 tokens per session scan A 21a475e0b50b

Subscribe to this mod's changes

chaos-experiment is a skill published in the GitHub repository harness/harness-ai (20 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 911 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to chaos-experiment, differing in 163 lines, and is treated as a copy.

DevOps and cloud Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

chaos-experiment