hivemind CLAUDE.md

hivemind CLAUDE.md is an instructions file for coding agents from dip497/hivemind. It costs 3,200 tokens per session, scanned A, original, MIT.

A guide to Hivemind's research workflow using Hyperresearch, a command-line tool that collects and organizes web research into notes. It explains the multi-step process and where its research files belong.

In plain words
What is it for?
Use it when researching a topic for Hivemind, running the Hyperresearch pipeline, or creating and reviewing research notes and reports.
Why use it?
It helps the coding assistant run research in the project's expected order and save results in the format and locations that Hivemind can use.

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/dip497/hivemind/claude-md
Clone the repo
git clone --depth 1 https://github.com/dip497/hivemind

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 hivemind CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dip497/hivemind/claude-md.svg)](https://agentmods.dev/instructions/dip497/hivemind/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dip497/hivemind/claude-md"><img src="https://agentmods.dev/badge/instructions/dip497/hivemind/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,200 This file is loaded in full into every session.
When invoked 3,200 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 $0.03200 $0.03200
Opus 5 $0.01600 $0.01600
Sonnet 5 $0.00640 $0.00640
Haiku 4.5 $0.00320 $0.00320

Measured 4d ago against content hash ebbb5d874b9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

CLAUDE.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE

Research Base (hyperresearch) — Today is 2026-05-17

CLI path: /home/dipendra-sharma/projects/hivemind/.venv/bin/hyperresearch — use this exact path for every hyperresearch command. It may not be on your system PATH.

Paths in this document are relative to your current working directory, not to the CLI binary's location. Use research/notes/final_report_<vault_tag>.md (not a prefix with the binary path) when you save files.

This project uses hyperresearch as an agent-driven research knowledge base. The research/ directory contains markdown notes collected from web sources and original research. Append --json to any command for structured output.

How to do research

Run a research session with /hyperresearch <query>. This invokes the V8 16-step pipeline. The entry skill at .claude/skills/hyperresearch/SKILL.md is a thin ROUTER. The 16 step procedures live in their own skills (hyperresearch-1-decompose through hyperresearch-16-readability-audit) and are loaded fresh into context via the Skill tool when each step runs. This solves V7's context-compaction problem: each step's procedure lands in context only when needed. Read the entry skill before you start a research session; it explains the chain mechanics.

Step 1 classifies the query into one of two tiers (light or full) and the rest of the pipeline scales accordingly — short bounded queries skip the depth investigations, critics, and patcher (~30-40 min); argumentative deep-research queries run all 16 steps with adversarial review (~1.5-2.5 hours).

Do NOT use WebFetch for source pages — use /home/dipendra-sharma/projects/hivemind/.venv/bin/hyperresearch fetch instead. The skill files explain when to fetch vs. search.

What the skill files own

The skill files own everything about how to research. That includes:

  • The pipeline phases and what each phase does
  • Which subagents exist and what each one is for (fetcher, loci-analyst, depth-investigator, 4 critics, patcher, polish-auditor)
  • The tool-lock invariant (patcher and polish-auditor can only Read + Edit, never Write)
  • The subagent spawn contract (every Task call passes the verbatim research_query + pipeline position + inputs)
  • Artifact locations (research/scaffold.md, research/prompt-decomposition.json, research/loci.json, research/comparisons.md, interim notes, patch / polish logs)
  • The curation pass after every research session

Read the full file on GitHub · 181 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 · 181 lines · 3,200 tokens per session scan A ebbb5d874b9e

Subscribe to this mod's changes

hivemind CLAUDE.md is an instructions file published in the GitHub repository dip497/hivemind (6 stars, last pushed today), licensed MIT. It adds 3,200 tokens to every session, about $0.0160 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

agor CLAUDE.md

Claude Code instructions for preset-io/agor, a project described as: Agor - team command center for all things agentic.

preset-io/agor · 3 tokens

agor AGENTS.md

AGENTS.md instructions for preset-io/agor, covering claude.md, important: where the docs live, quick start, terminal 1: daemon (watches core + daemon, auto-restarts) and terminal 2: ui dev server.

preset-io/agor · 7,016 tokens

pi-agent-dashboard AGENTS.md

AGENTS.md instructions for BlackBeltTechnology/pi-agent-dashboard, covering pi dashboard, docs-first gate — kb before grep (per-turn doctrine), code instructions (per-turn doctrine), investigation protocol — index first and documentation update protocol.

BlackBeltTechnology/pi-agent-dashboard · 3,640 tokens

Arcgentic CLAUDE.md

Claude Code instructions for Arch1eSUN/Arcgentic, covering arcgentic v0.2.0 — dev session handoff, 1. identity, 2. not-this (boundary), 3. where you are (state as of handoff) and files to be created (v0.2.0 p0 scope, per spec § 18).

Arch1eSUN/Arcgentic · 6,622 tokens

AIWorkHub AGENTS.md

AGENTS.md instructions for shrec/AIWorkHub, covering aiworkhub mcp agent notes and aiworkhub mcp tool-use policy.

shrec/AIWorkHub · 1,041 tokens

growmos AGENTS.md

Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.

codician-team/growmos · 606 tokens