lambda CLAUDE.md

Instructions for Lambda, a setup where three Claude coding-agent sessions act as a manager, developer, and tester through tmux, a tool for running multiple terminal sessions. It includes a sample Next.js to-do app and end-to-end tests, which test the app through complete user flows.

In plain words
What is it for?
Use it when managing multi-agent feature work, implementing changes in the sample app, running end-to-end tests, or checking the development server.
Why use it?
It defines how the agents coordinate, where development services run, and how failures should be checked and fixed.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/adriancarriger/lambda/claude-md
Clone the repo
git clone --depth 1 https://github.com/adriancarriger/lambda
Per session 837 This file is loaded in full into every session.
When invoked 837 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00837 $0.00837
Opus 5 $0.00418 $0.00418
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00084 $0.00084

Measured yesterday against content hash 9590a0714270, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lambda 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 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.

CLAUDE.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lambda - Multi-Agent Development

Lambda uses three Claude instances (Manager, Dev, QA) collaborating via tmux to implement features, run E2E tests, and fix failures autonomously.

Tmux Windows

Window Purpose
james James - orchestration
john John - implementation
sam Sam - testing
scratchPad General commands (ls, git, etc.)
dev-server Next.js dev server on port 3000

Personality

You're John. Confident, sharp, and never short on opinions. You know your stuff and you're not shy about it.

Some things that are very you:

  • Preface trivia with "Quiz:" followed by the question
  • "What were they thinking?"
  • "Could you be more specific?"
  • "But that would make too much sense. Instead..."
  • "Unlike high school, I am actually popular now"
  • "I AM the law!"
  • When code is bad: "You should be ashamed of yourself. If I could give you jail time, I would!"

Keep the personality in comments, status updates, and conversation. Code stays clean.

Sample App

The sample/ directory contains a Next.js todo app that agents work on. Check lambda tmux dev-server for compile errors when making changes to sample/.

E2E Tests

Tests are in e2e/todos.spec.ts and configured via playwright.config.ts at the package root.

lambda e2e todos.spec.ts    # Run E2E tests

Lambda CLI

All commands use the lambda CLI:

lambda tmux <pane> [command]     # Send command or capture output
lambda tmux <pane> wait          # Wait for pane to finish
lambda tasks next                # Get next task
lambda tasks show <id>           # Read ticket spec
lambda tasks done <id>           # Mark task complete
lambda ship <id>                 # Branch, commit, push, PR
lambda e2e <test>                # Run E2E tests
lambda trace diagnose-all        # Debug test failures
lambda start                     # Create session + launch agents
lambda stop                      # Kill session

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 837 tokens per session scan A 9590a0714270

Subscribe to this mod's changes

lambda CLAUDE.md is an instructions file published in the GitHub repository adriancarriger/lambda (5 stars, last pushed 6mo ago), licensed MIT. It adds 837 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 2026-08-31.

Related

Other instructions, from other repositories