What is hivemind CLAUDE.md?

Repository instructions for hivemind, a command-line tool where one AI model does coding work and another reviews decisions when needed. They cover setup commands, testing, and the tool's internal structure.

Running linting, formatting, all tests, or one selected test; invoking hivemind commands; and understanding how its executor and advisor models work together.

They give the coding agent the project's expected commands and workflow, reducing mistakes such as using the wrong Python environment or skipping checks after changes.

How itsmostafa/hivemind configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to itsmostafa/hivemind. 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/itsmostafa/hivemind/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/itsmostafa/hivemind

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/itsmostafa/hivemind/claude-md/github.svg)](https://agentmods.dev/instructions/itsmostafa/hivemind/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/itsmostafa/hivemind/claude-md"><img src="https://agentmods.dev/badge/instructions/itsmostafa/hivemind/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/itsmostafa/hivemind/claude-md"><img src="https://agentmods.dev/badge/instructions/itsmostafa/hivemind/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,001 This file is loaded in full into every session.

When invoked 1,001 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.

Model	Per session	Once invoked
Fable 5.1	$0.01001	$0.01001
Opus 5.5	$0.00400	$0.00400
Sonnet 5.5	$0.00200	$0.00200
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash e1ddb7fab9e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hivemind 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

# Run all checks (lint + format + tests) — always run after implementing code changes
task check

# Individual tasks
task lint        # ruff check
task format      # ruff format
task test        # pytest

# Run a single test
uv run pytest tests/test_executor.py::test_name -v

# Invoke the CLI (use uv run — the system entrypoint may use the wrong Python)
uv run hivemind init                        # scaffold ~/.hivemind/config.yml
uv run hivemind run --executor ollama/llama3 --advisor ollama/llama3 "Your task"
uv run hivemind chat                        # interactive REPL with state carryover
uv run hivemind trace traces/run.jsonl

Architecture

hivemind implements the "advisor strategy" pattern: an executor model handles the task turn-by-turn while an advisor model is consulted only when needed, controlling cost.

Data flow

User prompt → CLI / run_task() → ExecutorLoop
    → ModelClient (LiteLLM) → Executor model
    → DecisionPolicy.should_consult()  [checks gates + heuristics]
    → (if triggered) Advisor.consult() → Advisor model
    → inject AdvisorResponse as user message → next executor turn
    → [DONE] detected → return ExecutorResult

Key components

File	Role
`executor.py`	`ExecutorLoop` — drives conversation turns, injects advisor guidance, detects `[DONE]`
`policy.py`	`DecisionPolicy` — gates (budget/cooldown) + heuristics (explicit `[NEED_ADVICE]`, consecutive failures, low `[CONFIDENCE:X.X]`, stagnation via Jaccard similarity)
`advisor.py`	`Advisor` — serializes context to JSON, calls advisor model, parses structured `AdvisorResponse`
`models.py`	`ModelClient` — thin LiteLLM wrapper; tool-call loop for Tavily search; passes `api_base` through for local endpoints
`schemas.py`	Pydantic models: `hivemindConfig`, `ModelConfig`, `PolicyConfig`, `SearchConfig`, `ExecutorResult`, `AdvisorResponse`
`config.py`	`load_config()` + `merge_cli_overrides()` — YAML loading from `~/.hivemind/config.yml` with `${ENV_VAR}` expansion
`log.py`	`TraceLogger` — structured JSONL events per turn
`tracking.py`	`CostTracker` — token/cost accounting per role (executor vs advisor)
`cli.py`	Click CLI — `hivemind init`, `hivemind run`, and `hivemind trace` commands

Read the full file on GitHub · 66 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.

2mo ago First seen · 66 lines · 1,001 tokens per session scan A e1ddb7fab9e5

Subscribe to this mod's changes

hivemind CLAUDE.md is an instructions file published in the GitHub repository itsmostafa/hivemind (20 stars, last pushed 6mo ago), licensed MIT. It adds 1,001 tokens to every session, about $0.0040 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.

ai-agents ai-tools claude codex

hivemind CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hivemind CLAUDE.mditsmostafa/hivemind	Instructions file	20	6mo ago	MIT	A	1,001	Claude Code
vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetags	Instructions file	25	today	MIT	A	82	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot

hivemind: Instructions file for Claude Code