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/jhd3197/cachibot/claude-mdgit clone --depth 1 https://github.com/jhd3197/CachiBotWrote 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/jhd3197/cachibot/claude-md)<a href="https://agentmods.dev/instructions/jhd3197/cachibot/claude-md"><img src="https://agentmods.dev/badge/instructions/jhd3197/cachibot/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 5.1 | $0.00835 | $0.00835 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
CachiBot 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 6d 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 — 86 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
CachiBot is a security-focused AI agent that uses the Prompture library for structured LLM interactions. It features a Python backend (FastAPI) with WebSocket streaming and a React+TypeScript frontend.
Common Commands
Backend Development
pip install -e ".[dev]" # Install with dev dependencies
cachibot server # Start API server (port 5870)
cachibot "your prompt" # Run single prompt via CLI
cachibot -i # Interactive mode
pytest # Run all tests
pytest -v # Verbose test output
ruff check . # Lint Python code
ruff format . # Format Python code
mypy cachibot # Type check
Frontend Development
cd frontend
npm install # Install dependencies
npm run dev # Start Vite dev server (port 5173)
npm run build # Production build
npm run lint # ESLint
The frontend dev server proxies /api and /ws to http://127.0.0.1:5870.
Architecture
Backend (cachibot/)
- agent.py: Core
CachibotAgentdataclass wrapping Prompture's Agent with callbacks, tool registration, and Python sandbox - cli.py: Typer-based CLI with
cachibotandcachientry points - api/server.py: FastAPI app with lifespan management
- api/websocket.py: WebSocket streaming for real-time agent responses
- api/routes/: REST endpoints (chat, config, health, models)
- models/: Pydantic schemas for chat, config, jobs, websocket messages
- storage/: SQLite async database layer with repository pattern
Frontend (frontend/src/)
- stores/: Zustand state management with localStorage persistence
bots.ts: Bot/Chat/Jobs/Tasks storesui.ts: UI state (sidebar, themes)connections.ts: API connection state
- api/: REST client and WebSocket management
- components/: React components organized by feature (chat/, common/, dialogs/, layout/, views/)
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.
- 6d ago First seen · 86 lines · 835 tokens per session scan A bad5c2ef5504
CachiBot CLAUDE.md is an instructions file published in the GitHub repository jhd3197/CachiBot (19 stars, last pushed 6mo ago), licensed MIT. It adds 835 tokens to every session, about $0.0042 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
goclaw AGENTS.md
AGENTS.md instructions for nextlevelbuilder/goclaw, covering goclaw gateway, language, tech stack, project structure and key patterns.
goclaw CLAUDE.md
Claude Code instructions for nextlevelbuilder/goclaw, covering goclaw gateway, language, tech stack, project structure and key patterns.
heatherbot AGENTS.md
Instructions for dvoraknc/heatherbot, covering agents.md — bootstrap guide for coding agents, 0. tl;dr for an agent, 1. system requirements, 2. component & port map and 3. pre-flight checklist (gather these before installing).
openagent CLAUDE.md
Claude Code instructions for the-open-agent/openagent, covering claude.md, commands, architecture, backend (go / beego) and frontend (react).
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).