agentmods.dev

meet-edward: Instructions file for Claude Code

CLAUDE.md

meet-edward CLAUDE.md is an instructions file for Claude Code from ben4mn/meet-edward. It costs 17,058 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for Edward, a full-stack AI assistant with long-term memory. It covers commit rules, the application’s frontend and backend, required services, setup, and development commands.

In plain words
What is it for?
Use it when developing or running Edward. It helps with first-time setup, restarting the frontend or backend, and checking the frontend code.
Why use it?
It gives coding agents the project context and prevents setup mistakes, such as running the backend in the wrong environment or adding prohibited commit attribution.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

This is ben4mn/meet-edward's own configuration. It tells Claude Code how to work on meet-edward itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything meet-edward configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/edward/backend/.venv/bin/python.

not rated 5repo +1 changed 25d ago A scan 17,058 tokens original Apache-2.0
View source ↗ ben4mn/meet-edward meet-edward.com
Reuse

Borrowing it

Nothing to install: this file belongs to ben4mn/meet-edward. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ben4mn/meet-edward/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ben4mn/meet-edward

Made for: Claude Code.

Wrote 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.

agentmods badge for meet-edward CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ben4mn/meet-edward/claude-md/github.svg)](https://agentmods.dev/instructions/ben4mn/meet-edward/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ben4mn/meet-edward/claude-md"><img src="https://agentmods.dev/badge/instructions/ben4mn/meet-edward/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meet-edward CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 17,058 This file is loaded in full into every session.
When invoked 17,058 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.17058 $0.17058
Opus 5.5 $0.06823 $0.06823
Sonnet 5.5 $0.03412 $0.03412
Haiku 4.5 $0.01706 $0.01706

Measured 25d ago against content hash c5077ffa4858, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meet-edward 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 25d 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.

CLAUDE.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file guides Claude Code (claude.ai/code), and any AI assistant helping someone with Edward, in this repository. It is the short operating guide; the long form (the why, the dates and the incidents behind every rule) is in docs/architecture/, one file per subsystem. When you change a subsystem, update its file there, and this file only when a rule or an index line changes. backend/tests/test_doc_lint.py fails when either names a path, a route or a stream event that does not exist, or when this file passes 64 KiB (testing.md).

Commit rules

  • Do not add Co-Authored-By lines (or any other AI attribution) to commit messages in this repository.
  • Short conventional messages (feat: …, fix(scope): …, docs: …); a fix lands with the test that pins it.
  • Nothing personal goes into the tree: no names, numbers, hosts or paths of a real household. Code names the owner only through backend/services/owner.py and the host only through backend/services/host_config.py; examples use invented people (a partner Rowan, a friend Parker, a dog Biscuit), my-mac.local and edward.example.com. Never commit .env or backend/.jwt_secret.

Project overview

Edward is an open-source personal AI assistant with long-term memory that runs on its owner's Mac (Apache-2.0; github.com/ben4mn/meet-edward, meet-edward.com): Next.js (PWA) + FastAPI + PostgreSQL/pgvector, LangGraph for turns, the Claude API for every model call (ChatClaude, one route per purpose, a $5 daily spend cap by default). He works for one person, the owner, and answers in chat, voice and iMessage pings (anyone's @Edward, the owner's self-chat); works in his own sandboxed computer with one 14-tool set; can read the owner's messages and mail (opt-in) and notice what matters, saying it once through tell_owner; thinks on his own in wakes (follow-through, a silent nightly, free time at 13:00); keeps a thought journal of what he chooses to do; and shows himself on Today, an iPhone widget, the host Mac's screen and an optional household hub.

Read the full file on GitHub · 300 lines

Changes

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.

  1. 25d ago Changed · -296 lines · +9,043 tokens per session c5077ffa4858
  2. 2mo ago First seen · 596 lines · 8,015 tokens per session scan A 9db05265fcb2

Subscribe to this mod's changes

meet-edward CLAUDE.md is an instructions file published in the GitHub repository ben4mn/meet-edward (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 17,058 tokens to every session, about $0.0682 per session on Opus 5.5. 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 2026-08-31.

aiai-agentsai-assistantanthropicclaudeconversational-ai
Related

meet-edward CLAUDE.md compared with instructions from other repositories

meet-edward CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
meet-edward CLAUDE.mdben4mn/meet-edwardInstructions file524d agoApache-2.0A17,058Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode