agentmods.dev

labrat CLAUDE.md

labrat CLAUDE.md is an instructions file for coding agents from ProjectDXAI/labrat. It costs 619 tokens per session, scanned A, a copy of labrat AGENTS.md, MIT.

Repository instructions for Labrat, a tool that creates and manages research workspaces called labs. They identify the source documents and the files generated into each lab for Claude Code and Codex.

In plain words
What is it for?
Use them when maintaining Labrat, editing its templates, changing generated-lab files, updating documentation, or keeping Claude Code and Codex support in sync.
Why use it?
They keep the two coding-agent interfaces aligned and prevent generated labs from missing the instructions, skills, commands, or prompts needed to operate.

Instructions file

not rated 239 27d ago A scan 619 tokens copy · 92% MIT
View the source file ProjectDXAI/labrat
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/projectdxai/labrat/claude-md
Clone the repo
git clone --depth 1 https://github.com/ProjectDXAI/labrat

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 labrat CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/projectdxai/labrat/claude-md.svg)](https://agentmods.dev/instructions/projectdxai/labrat/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/projectdxai/labrat/claude-md"><img src="https://agentmods.dev/badge/instructions/projectdxai/labrat/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 619 This file is loaded in full into every session.
When invoked 619 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod 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 $0.00619 $0.00619
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 4d ago against content hash 70fa6de9c21c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

labrat 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 4d 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.

Origin

This is a copy

92% identical to labrat AGENTS.md — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

labrat repo

This is the repository root, not a runnable lab directory.

Use this file when working on labrat itself from Claude Code.

If Claude Code is opened inside a nested lab that has its own CLAUDE.md, follow the lab-local file for runtime operation. This root file governs repo maintenance, scaffold consistency, releases, and docs.

Source Of Truth

  • Product/setup docs: README.md, program.md, docs/getting-started.md, docs/runners.md, docs/MODEL_GUIDANCE.md
  • Scaffolded lab UX: templates/AGENTS.md, templates/CLAUDE.md, templates/.agents/skills/, templates/.claude/commands/, templates/agent_prompts/
  • Canonical example lab: examples/nlp-sentiment/research_lab/
  • Packaging/versioning: pyproject.toml, labrat/__init__.py, CHANGELOG.md

Interface Rules

  • Keep Claude Code and Codex first-class. If a lab gets one operator surface, add the matching one for the other interface.
  • Generated labs should ship AGENTS.md, .agents/skills/, CLAUDE.md, .claude/commands/, and agent_prompts/.
  • Keep CLAUDE.md durable and command-focused. Put shared phase details in agent_prompts/.
  • Do not require a hidden local setup for basic operation. The runnable contract should live in the repo.
  • When operator guidance changes, keep templates, the canonical example lab, and the docs in sync.
  • Prefer labrat ... examples in docs when working from the repo root. Keep the copied scripts/*.py flow valid inside labs.

Frontier Model Rules

  • Use docs/MODEL_GUIDANCE.md for model and prompt-process updates.
  • GPT-5.5 is a Codex host selection, not a lab runtime constant. Do not hardcode API model IDs into labrat for Codex usage.
  • Prefer explicit completion and verification contracts over broad encouragement.
  • Reserve high reasoning effort for design, audit, frame break, profile authoring, and release work.

Checks

  • . .venv/bin/activate && labrat doctor --lab-dir examples/nlp-sentiment/research_lab
  • . .venv/bin/activate && labrat next-prompt --lab-dir examples/nlp-sentiment/research_lab --runner claude --phase auto
  • . .venv/bin/activate && labrat next-prompt --lab-dir examples/nlp-sentiment/research_lab --runner codex --phase auto
  • . .venv/bin/activate && make smoke

Read the full file on GitHub · 44 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. 4d ago First seen · 44 lines · 619 tokens per session scan A 70fa6de9c21c

Subscribe to this mod's changes

labrat CLAUDE.md is an instructions file published in the GitHub repository ProjectDXAI/labrat (239 stars, last pushed 27d ago), licensed MIT. It adds 619 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to labrat AGENTS.md, differing in 13 lines, and is treated as a copy.

Multi-AgentResearchai-agentsautonomous-researchclaude-codeexperiment-managementresearch-automation
Related

Other instructions, from other repositories

Svatah CLAUDE.md

Instructions for bayeslabs-rsi/Svatah, covering svatah, architecture overview, key concepts, workspace & state and experiment lifecycle.

bayeslabs-rsi/Svatah · 2,351 tokens

agentic-rd-skill AGENTS.md

AGENTS.md instructions for TheStreamCode/agentic-rd-skill, covering repository instructions, purpose and sources of truth, repository invariants, implementation style and documentation synchronization.

TheStreamCode/agentic-rd-skill · 1,439 tokens

solo AGENTS.md

AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.

solo-agent/solo · 306 tokens

research-os AGENTS.md

Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).

lxinfei5/research-os · 1,143 tokens

AI-System-Design-Consultant CLAUDE.md

Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.

deepanshu2711/AI-System-Design-Consultant · 674 tokens

agent-eve CLAUDE.md

Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).

shehryarsaroya/agent-eve · 9,010 tokens