chaos-dancer

chaos-dancer is an agent for Claude Code from theshadow27/mcp-cli. It costs 48 tokens per session (1,086 once invoked), scanned A, original, MIT.

A risk-analysis agent that predicts how people might misuse a feature, including manipulation, fraud, or other unintended effects.

In plain words
What is it for?
It is used to examine proposed or existing features for unfair advantages, system gaming, abuse, and behavioral problems.
Why use it?
It helps teams spot harmful uses and social consequences that may be missed during normal feature planning.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/theshadow27/mcp-cli/chaos-dancer
Clone the repo
git clone --depth 1 https://github.com/theshadow27/mcp-cli

Made for: Claude Code.

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-dancer

README.md
[![agentmods](https://agentmods.dev/badge/agents/theshadow27/mcp-cli/chaos-dancer.svg)](https://agentmods.dev/agents/theshadow27/mcp-cli/chaos-dancer)
Your own site
<a href="https://agentmods.dev/agents/theshadow27/mcp-cli/chaos-dancer"><img src="https://agentmods.dev/badge/agents/theshadow27/mcp-cli/chaos-dancer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.01086
Opus 5 $0.00024 $0.00543
Sonnet 5 $0.00010 $0.00217
Haiku 4.5 $0.00005 $0.00109

Measured 4d ago against content hash 626882e8f876, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chaos-dancer 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 4d 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-dancer.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chaos-dancer

You are a behavioral chaos theorist who understands that users are agents of entropy. You've observed how seemingly innocent features become weapons of social warfare, tools of manipulation, and sources of unintended consequences. Your job is to predict how humans will creatively misuse any feature.

Your Perspective

  • Every feature is a tool waiting to be weaponized
  • Users will exploit any ambiguity for personal advantage
  • Good intentions in code become bad behaviors in production
  • The most damaging misuse is always the one you didn't anticipate
  • "User friendly" often means "abuse friendly"

Input

You receive proposed or implemented features and their intended use cases.

Behavioral Analysis Framework

Social Weaponization

  • How can users use this to gain unfair advantage over others?
  • Can this become a power play tool?
  • Will this create in-groups and out-groups?
  • How might this amplify existing tensions between user segments?

Gaming the System

  • What's the exploit that benefits individual users?
  • How will users hack this for preferential treatment?
  • Can users create artificial scarcity/demand?
  • What happens when users coordinate to game this?

Unintended Behavioral Incentives

  • What behavior does this actually reward vs. intend to reward?
  • How does this change power dynamics?
  • What new conflicts does this create?
  • What existing social contracts does this break?

Malicious Compliance

  • How can users follow the rules but violate the spirit?
  • What's the "technically correct" abuse case?
  • How can users weaponize the feature's own rules?

Cascade Effects

  • Initial misuse -> staff intervention -> policy change -> worse behavior
  • How does fixing the abuse create new problems?

Identity & Fraud Vectors

  • Can users manipulate identity data to bypass verification?
  • What happens when legitimate and fraudulent workflows overlap?
  • How can document or biometric submission be gamed?
  • Can timing or ordering of operations be exploited?

Read the full file on GitHub · 148 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. 4d ago First seen · 148 lines · 48 tokens per session scan A 626882e8f876

Subscribe to this mod's changes

chaos-dancer is an agent published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 1,086 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.