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/easydevv/pyhunt/agents-mdgit clone --depth 1 https://github.com/EasyDevv/pyhuntWhat 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 | $0.00943 | $0.00943 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
pyhunt AGENTS.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 yesterday.
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 — 146 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.
Project Overview
pyhunt is a lightweight Python logging tool that automatically traces function calls and provides visual, tree-structured colored logs for debugging. It uses a simple @trace decorator to log function execution times, call hierarchies, and exceptions.
Development Commands
Package Management
# Install dependencies
uv sync
# Build the package
uv build
Python Execution
# Run Python files with uv
uv run python filename.py
# Run Python modules with uv
uv run python -m module_name
# Run Python interactively with uv
uv run python
Testing
# Run all tests
uv run pytest
# Run specific test file
uv run pytest test/test_examples.py
# Run tests with verbose output
uv run pytest -v
Code Quality
# Lint all files in the current directory
uvx ruff check
# Format all files in the current directory
uvx ruff format
CLI Tool
# Set up environment file (creates .env with DEBUG level)
hunt
# Set specific log levels
hunt --debug
hunt --info
hunt --warning
hunt --error
hunt --critical
# Set root directory and repeat limit
hunt --root
hunt --repeat 5
Core Architecture
Main Components
pyhunt/decorator.py: Core@tracedecorator implementation for function call tracingpyhunt/cli.py: Command-line interface for managing log levels and environment variablespyhunt/logger.py: Direct logging interface for manual log messagespyhunt/console.py: Console output formatting and color handlingpyhunt/config.py: Environment variable configuration and.envfile managementpyhunt/colors.py: Color definitions for different log levelspyhunt/context.py: Call context management for tracking execution depthpyhunt/utils.py: Utility functions for path handling and formattingpyhunt/helpers.py: Helper functions for decorator and logging operations
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.
- yesterday First seen · 146 lines · 943 tokens per session scan A e09a9b78694b
pyhunt AGENTS.md is an instructions file published in the GitHub repository EasyDevv/pyhunt (45 stars, last pushed 11mo ago), licensed MIT. It adds 943 tokens to every session, about $0.0047 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
evlog AGENTS.md
Instructions for HugoRCD/evlog, covering evlog, commands, monorepo structure, conventions and code style: no slop.
tslog AGENTS.md
Instructions for fullstack-build/tslog, covering project overview, settings are grouped (v5), quick reference, build system and build configs.
inspector copilot-instructions.md
Copilot instructions for modelcontextprotocol/inspector, covering copilot review instructions — mcp inspector, typescript, react and ui (web client), the .withprops() rule and state and effects.
rsyslog modules.plugins.instructions.md
Instructions for rsyslog/rsyslog, a project described as: High-performance log ingestion and ETL engine.
rsyslog docs.instructions.md
Instructions for rsyslog/rsyslog: Read first: AGENTS.md and any doc structure guidance it references.
rsyslog modules.contrib.instructions.md
Instructions for rsyslog/rsyslog: Follow the same rules as for plugins/, but additionally.