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/ben4mn/meet-edward/claude-mdgit clone --depth 1 https://github.com/ben4mn/meet-edwardWrote 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/ben4mn/meet-edward/claude-md)<a href="https://agentmods.dev/instructions/ben4mn/meet-edward/claude-md"><img src="https://agentmods.dev/badge/instructions/ben4mn/meet-edward/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 | $0.08015 | $0.08015 |
| Opus 5 | $0.04007 | $0.04007 |
| Sonnet 5 | $0.01603 | $0.01603 |
| Haiku 4.5 | $0.00801 | $0.00801 |
Grade A, and why
meet-edward CLAUDE.md scanned grade A with 2 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Shell** (`shell_execution.py`): Bash with blocklist (sudo, curl, docker, etc.), restricted env Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **JavaScript** (`javascript_execution.py`): Node.js subprocess, blocked network/child_process modules How it starts
The opening of the file, as written. The whole thing — 596 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.
Commit Rules
- Do NOT add
Co-Authored-Bylines to any commit messages in this repository. No Claude attribution in git history.
Project Overview
Edward is a full-stack AI assistant with long-term memory, built with Next.js, FastAPI, and PostgreSQL. Uses LangGraph for conversation orchestration and pgvector for memory retrieval.
Running the App
The backend must run natively on macOS (not in a container). This is required for the scheduled events scheduler and AppleScript/MCP integrations.
# First-time setup
./setup.sh # Creates venv, installs deps, sets up .env
# Recommended: restart script (handles both services)
./restart.sh # Restart both frontend + backend
./restart.sh frontend # Restart only frontend
./restart.sh backend # Stop and restart only backend
# Individual services
cd backend && ./start.sh # Backend (FastAPI :8000)
cd frontend && npm install && npm run dev # Frontend (Next.js :3000)
# Lint frontend
cd frontend && npm run lint
After initial setup, ./start.sh handles venv activation and auto-installs new dependencies.
Build frontend for production
cd frontend && npm run build
Architecture
Frontend (Next.js :3000) → Backend (FastAPI :8000) → PostgreSQL (:5432)
↓
LangGraph Agent
↓
Claude API (Anthropic)
Frontend Routes
| Route | Auth | Description |
|---|---|---|
/ |
Public | Redirects to /login |
/login |
Public | Password login (AuthProvider only, no app shell) |
/chat |
Protected | Main chat interface (full app shell) |
/settings |
Protected | Settings page |
Route wrappers controlled by ConditionalLayout.tsx:
/→ redirects to/login/login→<AuthProvider>only- Everything else →
<AuthProvider>→<AuthGuard>→<ChatProvider>→<ClientLayout>
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.
- 5d ago First seen · 596 lines · 8,015 tokens per session scan A 9db05265fcb2
meet-edward CLAUDE.md is an instructions file published in the GitHub repository ben4mn/meet-edward (4 stars, last pushed 11d ago), licensed Apache-2.0. It adds 8,015 tokens to every session, about $0.0401 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
golemcore-bot CLAUDE.md
Instructions for alexk-dev/golemcore-bot, covering claude.md — golemcore bot, build & test, modules, architecture and package structure.
golemcore-bot AGENTS.md
Instructions for alexk-dev/golemcore-bot, a project described as: Agent Platform for AI-Native Companies.
LIA-Assistant AGENTS.md
AGENTS.md instructions for jgouviergmail/LIA-Assistant, covering agents.md, project overview, build & development commands, full setup (backend + frontend + git hooks) and stop.
LIA-Assistant CLAUDE.md
Claude Code instructions for jgouviergmail/LIA-Assistant, covering claude.md, project overview, build & development commands, full setup (backend + frontend + git hooks) and stop.
wisp-science AGENTS.md
AGENTS.md instructions for xuzhougeng/wisp-science, covering agents.md, project orientation, repository layout, engineering rules and verification commands.
ai-agents security.instructions.md
Instructions for rjmurillo/ai-agents, covering security file rules, must, should, must not and references.