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.
npx agentmods add instructions/panbanda/omen/claude-mdgit clone --depth 1 https://github.com/panbanda/omenWrote 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/instructions/panbanda/omen/claude-md)<a href="https://agentmods.dev/instructions/panbanda/omen/claude-md"><img src="https://agentmods.dev/badge/instructions/panbanda/omen/claude-md.svg" alt="Measured on agentmods" 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 | $0.02727 | $0.02727 |
| Opus 5 | $0.01363 | $0.01363 |
| Sonnet 5 | $0.00545 | $0.00545 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
omen CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build and Development Commands
# Setup git hooks (run once after clone)
lefthook install
# Format code
cargo fmt
# Run linter
cargo clippy --all-targets --all-features -- -D warnings
# Run all tests
cargo test
# Run tests with coverage
cargo llvm-cov --all-features --ignore-filename-regex 'main\.rs$'
# Build release binary
cargo build --release
# Run a single test
cargo test test_complexity_simple
# Run tests for a specific module
cargo test analyzers::complexity
Architecture
Omen is a multi-language code analysis CLI built in Rust. It uses tree-sitter for parsing source code across 13 languages.
Module Structure
src/
cli/ - CLI entry point using clap
config/ - Configuration loading and schema
core/ - Core types and traits
analyzers/ - Analysis implementations
complexity.rs - Cyclomatic and cognitive complexity
satd.rs - Self-admitted technical debt
deadcode.rs - Unused code detection
churn.rs - Git history file churn
duplicates.rs - Code clone detection (MinHash+LSH)
defect.rs - Defect probability (PMAT)
changes.rs - JIT commit-level risk
tdg.rs - Technical Debt Gradient
graph.rs - Dependency graph (Mermaid)
hotspot.rs - High churn + complexity
temporal.rs - Temporal coupling
ownership.rs - Code ownership and bus factor
cohesion.rs - CK metrics (WMC, CBO, RFC, LCOM4, DIT, NOC)
repomap.rs - PageRank-ranked symbols
outline.rs - File and symbol outlines
impact.rs - Symbol blast-radius analysis
smells.rs - Architectural smells (Tarjan SCC)
flags.rs - Feature flag detection
mutation/ - Mutation testing (21 operators, parallel execution)
semantic/ - TF-IDF indexing, search, cache, and multi-repo support
context.rs - Agent-oriented repository context
symbol.rs - Symbol lookup and relationship reports
git/ - Git operations (log, blame, diff)
parser/ - Tree-sitter wrapper
mcp/ - MCP server for LLM integration
output/ - Output formatting (JSON/Markdown/text)
report/ - minijinja report rendering and embedded HTML template
score/ - Repository health scoring
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.
- 4d ago First seen · 234 lines · 2,727 tokens per session scan A 30eee013660a
omen CLAUDE.md is an instructions file published in the GitHub repository panbanda/omen (19 stars, last pushed today), licensed Apache-2.0. It adds 2,727 tokens to every session, about $0.0136 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.
Other instructions, from other repositories
roam-code AGENTS.md
AGENTS.md instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
truecourse CLAUDE.md
Claude Code instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.
truecourse AGENTS.md
AGENTS.md instructions for truecourse-ai/truecourse, covering truecourse — codex instructions, key files to keep updated, project layout, development commands and rules.
claude-ruby-marketplace CLAUDE.md
Instructions for hoblin/claude-ruby-marketplace, covering claude.md, repository purpose, before editing, directory structure and versioning.
invigil AGENTS.md
AGENTS.md instructions for invigil/invigil, covering agents.md — conventions for ai coding agents, build / test / lint and layout.
mcp-server AGENTS.md
AGENTS.md instructions for The-Code-Registry/mcp-server, covering agents.md, mcp endpoints, discovery, client compatibility note (cursor / callmcptool wrappers) and authentication.