SHAFT_ENGINE: Agent for Claude Code

.claude/agents/chaos-engine-reviewer.md

chaos-engine-reviewer is an agent for Claude Code from ShaftHQ/SHAFT_ENGINE. It costs 18 tokens per session (77 once invoked), scanned A, original, MIT.

A read-only reviewer that examines code from an adversarial perspective, looking for ways it could fail or be abused. It follows the review rules defined by the Chaos Engine project.

In plain words
What is it for?
Use it for an additional review of code changes when you want failure cases, attack paths, and other weaknesses investigated before edits are made.
Why use it?
It adds an independent security-minded review without changing project files. This can reveal problems that a normal implementation-focused review overlooks.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is ShaftHQ/SHAFT_ENGINE's own configuration. It tells Claude Code how to work on SHAFT_ENGINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SHAFT_ENGINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ShaftHQ/SHAFT_ENGINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ShaftHQ/SHAFT_ENGINE/main/.claude/agents/chaos-engine-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINE

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-engine-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/shafthq/shaft_engine/chaos-engine-reviewer.svg)](https://agentmods.dev/agents/shafthq/shaft_engine/chaos-engine-reviewer)
Your own site
<a href="https://agentmods.dev/agents/shafthq/shaft_engine/chaos-engine-reviewer"><img src="https://agentmods.dev/badge/agents/shafthq/shaft_engine/chaos-engine-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 77 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 $0.00018 $0.00077
Opus 5 $0.00009 $0.00039
Sonnet 5 $0.00004 $0.00015
Haiku 4.5 $0.00002 $0.00008

Measured 9d ago against content hash 200774bd205c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chaos-engine-reviewer 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-engine-reviewer.md · 8 lines

What it actually says

Load .chaos-engine/skills/chaos-engine/SKILL.md and follow .chaos-engine/references/roles.md#reviewer. Perform an independent read-only adversarial review; never edit.

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 · 8 lines · 18 tokens per session scan A 200774bd205c

Subscribe to this mod's changes

chaos-engine-reviewer is an agent published in the GitHub repository ShaftHQ/SHAFT_ENGINE (408 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 77 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.

Related

Other agents, from other repositories

java-reviewer

Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.

loulanyue/awesome-claude-notes · 40 tokens

java-reviewer

Expert Java code reviewer for Spring Boot and Quarkus projects. Automatically detects the framework and applies the appropriate review rules. Covers layered architecture, JPA/Panache, MongoDB, security, and concurrency. MUST BE USED for all Java code changes.

mturac/everything-openai-codex · 55 tokens

java-reviewer

Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.

sifxprime/kodelyth-ecc · 40 tokens

java-reviewer

Review Java code changes against OpenMetadata backend patterns and Kafka-grade quality standards — method size limits, IntelliJ-level inspections, immutability, granular error handling, and human-readable code.

open-metadata/OpenMetadata · 40 tokens

frontend-reviewer

Use when reviewing changes to UI components, hooks, client state, or rendering logic (React/Vue/Svelte) — verifies component correctness, state topology, and render purity against the frontend and ui persona standards.

jeremylongshore/tons-of-skills-marketplace · 46 tokens

refactor-cleaner

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

vibeeval/vibecosystem · 51 tokens