agentmods.dev

haive: Instructions file for Claude Code

CLAUDE.md

haive CLAUDE.md is an instructions file for Claude Code from pr1m8/haive. It costs 4,711 tokens per session, scanned A, original, MIT.

A project guide for Haive, a framework for building AI agents. It explains the monorepo structure, where the framework’s guides live, and rules for agent design, state, memory, and graphs.

In plain words
What is it for?
Developing Haive agents, including multi-agent workflows, memory systems, custom graph nodes, and state schemas.
Why use it?
It gives coding agents the project’s architecture and required conventions before they change code across its separate packages.

Instructions file for Claude Code

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

This is pr1m8/haive's own configuration. It tells Claude Code how to work on haive 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 haive configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/will/Projects/haive.

not rated 24repo 6mo ago A scan 4,711 tokens original MIT
View source ↗ pr1m8/haive
Reuse

Borrowing it

Nothing to install: this file belongs to pr1m8/haive. 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/pr1m8/haive/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pr1m8/haive

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 haive CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pr1m8/haive/claude-md/github.svg)](https://agentmods.dev/instructions/pr1m8/haive/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pr1m8/haive/claude-md"><img src="https://agentmods.dev/badge/instructions/pr1m8/haive/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 haive CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pr1m8/haive/claude-md"><img src="https://agentmods.dev/badge/instructions/pr1m8/haive/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,711 This file is loaded in full into every session.
When invoked 4,711 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 $0.04711 $0.04711
Opus 5.5 $0.01884 $0.01884
Sonnet 5.5 $0.00942 $0.00942
Haiku 4.5 $0.00471 $0.00471

Measured 2mo ago against content hash 3f68f221a693, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

haive 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 · 536 lines

How it starts

The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Haive Agent Framework

Version: 5.0 Last Updated: 2026-04-06

Project Context

  • Directory: /home/will/Projects/haive
  • Branch: final-refactor
  • Structure: Monorepo with Git submodules (7 packages)
  • Core Rules:
    • Always use poetry run prefix for ALL Python commands
    • Real components only - NO MOCKS EVER in tests
    • Always use explicit imports: from haive.core.*
    • Be EXTREMELY careful with submodules - each is its own repo

Guides & Documentation

Agent Design (NEW — 2026-04-06)

  • @project_docs/guides/agent/AGENT_DESIGN_PATTERNS.md — How to build agents around BaseGraph, state schemas, SimpleAgent/ReactAgent/MultiAgent patterns, anti-patterns
  • @project_docs/guides/agent/MULTIAGENT_STATE_DESIGN.md — Complex state schemas for multi-agent systems, sequential/parallel/conditional patterns
  • @project_docs/guides/agent/CUSTOM_NODES_AND_GRAPHS.md — Custom nodes, graph patterns (branching, parallel, reflection loops), NodeConfig types
  • @project_docs/guides/agent/MEMORY_AGENT_GUIDE.md — Memory + KG integration, Neo4j Cypher, store namespaces, docker-compose
  • @project_docs/guides/agent/STATE_SCHEMA_NOTES.md — State flow research, engine injection fix, schema hierarchy

Architecture

  • @project_docs/active/architecture/state_schema_engine_gap.md — How engines flow through state (FIXED)
  • @project_docs/active/architecture/multi_agent_meta_agent_memory_hub.md — Multi-agent architecture decisions
  • @project_docs/active/architecture/agent_as_tool_pattern.md — Agent-as-tool composition
  • @project_docs/guides/TOOL_ROUTING_REFACTOR.md — Tool routing: pydantic_model vs pydantic_tool vs parse_output

Standards

  • @project_docs/active/standards/coding/PYDANTIC_PATTERNS.md — Pydantic best practices
  • @project_docs/active/standards/testing/philosophy.md — No-mocks testing
  • @project_docs/active/standards/git/workflow.md — Git safety protocol

Quick Reference

Essential Imports

Read the full file on GitHub · 536 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 · 536 lines · 4,711 tokens per session scan A 3f68f221a693

Subscribe to this mod's changes

haive CLAUDE.md is an instructions file published in the GitHub repository pr1m8/haive (24 stars, last pushed 6mo ago), licensed MIT. It adds 4,711 tokens to every session, about $0.0188 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.

Building agentsLLMLangChainai-agentsframeworkknowledge-graphlanggraph
Related

haive CLAUDE.md compared with instructions from other repositories

haive CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
haive CLAUDE.mdpr1m8/haiveInstructions file246mo agoMITA4,711Claude 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