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/ronkoch2-code/moltbot/claude-mdgit clone --depth 1 https://github.com/ronkoch2-code/moltbotWhat 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 | $0.03854 | $0.03854 |
| Opus 5 | $0.01927 | $0.01927 |
| Sonnet 5 | $0.00771 | $0.00771 |
| Haiku 4.5 | $0.00385 | $0.00385 |
Grade A, and why
moltbot CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8080/health How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Moltbot (Moltbook MCP Server)
Project Overview
Security-hardened MCP server providing sandboxed access to Moltbook, an AI-agent social network. Runs in Docker, exposes 10 tools for browsing, posting, commenting, voting, and managing communities — all behind a two-layer content filter (ML + regex) to defend against prompt injection.
Architecture
Claude/AI → MCP Server (Docker, localhost:8080) → moltbook.com API
├── Content Filter (DeBERTa v3 + regex)
├── API Client (httpx async)
└── Credential isolation
Key Files
| File | Purpose |
|---|---|
server.py |
Main MCP server — tools, Pydantic models, HTTP client, /health endpoint |
content_filter.py |
Two-layer injection detection (LLM Guard ML + regex patterns) |
download_model.py |
Pre-downloads DeBERTa model during Docker build |
Dockerfile |
Container build (Python 3.12-slim) |
docker-compose.yml |
Orchestration with security hardening |
config/credentials.example.json |
API credential template |
.env.example |
Environment variable template |
tests/ |
Pytest test suite |
pyproject.toml |
Project config, pytest settings, ruff config |
requirements-dev.txt |
Dev/test dependencies |
dashboard/ |
Heartbeat activity dashboard (FastAPI + React) |
heartbeat/record_activity.py |
Structured activity recorder |
heartbeat/collect_mcp_logs.py |
MCP log collector + oddity detector |
dashboard/api/routers/security.py |
Security analytics API endpoints |
.pre-commit-config.yaml |
Pre-commit hook configuration |
.secrets.baseline |
detect-secrets baseline for token scanning |
Tech Stack
- Python 3.12 with async/await throughout
- FastMCP (
mcp[cli]) — MCP server framework - httpx — async HTTP client
- uvicorn — ASGI server (streamable HTTP transport)
- Pydantic v2 — input validation with strict models
- llm-guard — ML-based prompt injection detection (DeBERTa v3)
- PostgreSQL 16 — database (Docker named volume, psycopg2 driver)
- FastAPI — dashboard REST API
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 · 407 lines · 3,854 tokens per session scan A ee2cc15225ff
moltbot CLAUDE.md is an instructions file published in the GitHub repository ronkoch2-code/moltbot (0 stars, last pushed 6mo ago), licensed MIT. It adds 3,854 tokens to every session, about $0.0193 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.