agentmods.dev

awaithumans-human-in-the-loop-ai-agents: Instructions file for Claude Code

CLAUDE.md

awaithumans-human-in-the-loop-ai-agents CLAUDE.md is an instructions file for Claude Code from awaithumans/awaithumans-human-in-the-loop-ai-agents. It costs 4,501 tokens per session, scanned A, original, Apache-2.0.

Repository rules for Awaithubmans, an open-source system that lets AI agents hand tasks to people for review or completion. The project is organized as a monorepo, meaning several related packages live in one repository, including Python, dashboard, and TypeScript components.

In plain words
What is it for?
Use them when changing the Python package, web dashboard, TypeScript SDK, or their shared monorepo structure.
Why use it?
They give developers and coding agents a shared source of truth for the project’s architecture, package boundaries, and coding decisions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is awaithumans/awaithumans-human-in-the-loop-ai-agents's own configuration. It tells Claude Code how to work on awaithumans-human-in-the-loop-ai-agents 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 awaithumans-human-in-the-loop-ai-agents configures →

not rated 27repo 17d ago A scan 4,501 tokens original Apache-2.0
View source ↗ awaithumans/awaithumans-human-in-the-loop-ai-agents awaithumans.dev
Reuse

Borrowing it

Nothing to install: this file belongs to awaithumans/awaithumans-human-in-the-loop-ai-agents. 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/awaithumans/awaithumans-human-in-the-loop-ai-agents/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/awaithumans/awaithumans-human-in-the-loop-ai-agents

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 awaithumans-human-in-the-loop-ai-agents CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/awaithumans/awaithumans-human-in-the-loop-ai-agents/claude-md/github.svg)](https://agentmods.dev/instructions/awaithumans/awaithumans-human-in-the-loop-ai-agents/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/awaithumans/awaithumans-human-in-the-loop-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/awaithumans/awaithumans-human-in-the-loop-ai-agents/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 awaithumans-human-in-the-loop-ai-agents CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/awaithumans/awaithumans-human-in-the-loop-ai-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/awaithumans/awaithumans-human-in-the-loop-ai-agents/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,501 This file is loaded in full into every session.
When invoked 4,501 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 $0.04501 $0.04501
Opus 5.5 $0.01800 $0.01800
Sonnet 5.5 $0.00900 $0.00900
Haiku 4.5 $0.00450 $0.00450

Measured 2mo ago against content hash 82ce88da94eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

awaithumans-human-in-the-loop-ai-agents 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 2mo 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 · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

awaithumans — Codebase Guide

This file is the source of truth for how code is written in this repo. It is read by human developers, AI coding agents (Claude Code, Copilot, Cursor), and CI. Follow it exactly.

What This Project Is

An open source infrastructure package that lets AI agent workflows delegate tasks to human beings — with task routing, notifications (Slack, email), a review dashboard, AI verification of completed work, and a callback system to resume the agent when the human is done.

One primitive: await_human() / awaitHuman() — the agent awaits a human like it awaits a promise.

Architecture Overview

The project has three packages:

  1. Python package (packages/python/) — the API server, CLI, channels, verification, AND the Python SDK. Published as awaithumans on PyPI. This is the brain of the system.

  2. Dashboard (packages/dashboard/) — Next.js 16 web UI. Pre-built to static files and bundled into the Python package for production. Separate dev server for development.

  3. TypeScript SDK (packages/typescript-sdk/) — the npm awaithumans package. A thin HTTP client to the Python API server. Includes adapter subpath exports for Temporal and LangGraph.

Developer's agent code                  The awaithumans system
─────────────────────                   ──────────────────────

  Python agent                           ┌─────────────────────────┐
  ┌──────────────┐      HTTP             │  API Server (Python)    │
  │ from         │ ──────────────────►   │  FastAPI + SQLModel     │
  │ awaithumans  │                       │                         │
  │ import       │                       │  Owns:                  │
  │ await_human  │                       │  - Task store (DB)      │
  └──────────────┘                       │  - Slack channel        │
                                         │  - Email channel        │
  TypeScript agent                       │  - AI verification      │
  ┌──────────────┐      HTTP             │  - Webhook dispatch     │
  │ import {     │ ──────────────────►   │  - Long-poll endpoint   │
  │  awaitHuman  │                       │  - Audit trail          │
  │ } from       │                       └────────────┬────────────┘
  │ "awaithumans"│                                    │
  └──────────────┘                                    │ serves static files
                                         ┌────────────▼────────────┐
                                         │  Dashboard (Next.js)    │
                                         │  Pre-built static files │
                                         │  Task queue, audit log  │
                                         └─────────────────────────┘

Read the full file on GitHub · 401 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. 2mo ago First seen · 401 lines · 4,501 tokens per session scan A 82ce88da94eb

Subscribe to this mod's changes

awaithumans-human-in-the-loop-ai-agents CLAUDE.md is an instructions file published in the GitHub repository awaithumans/awaithumans-human-in-the-loop-ai-agents (27 stars, last pushed 17d ago), licensed Apache-2.0. It adds 4,501 tokens to every session, about $0.0180 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 2026-08-30.

agent-workflowagentic-aiai-agentsai-infrastructurehitlhuman-in-the-loop
Related

awaithumans-human-in-the-loop-ai-agents CLAUDE.md compared with instructions from other repositories

awaithumans-human-in-the-loop-ai-agents CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
awaithumans-human-in-the-loop-ai-agents CLAUDE.mdawaithumans/awaithumans-human-in-the-loop-ai-agentsInstructions file2717d agoApache-2.0A4,501Claude 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