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.
npx agentmods add instructions/moonx010/hive-memory/claude-mdgit clone --depth 1 https://github.com/moonx010/hive-memoryWrote 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.
[](https://agentmods.dev/instructions/moonx010/hive-memory/claude-md)<a href="https://agentmods.dev/instructions/moonx010/hive-memory/claude-md"><img src="https://agentmods.dev/badge/instructions/moonx010/hive-memory/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02134 | $0.02134 |
| Opus 5 | $0.01067 | $0.01067 |
| Sonnet 5 | $0.00427 | $0.00427 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
hive-memory 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hive Memory — Unified Memory System for AI Agents
Project Overview
MCP server that gives AI agents persistent, browsable memory across projects and domains. Evolving from single-developer coding memory (v2) toward company-wide context layer (v3). Stores entities (decisions, learnings, documents, conversations, people) in a SQLite-backed graph with FTS5 search, synapse connections, and Hebbian learning.
Tech Stack
- TypeScript, Node.js (ES modules)
- MCP SDK (
@modelcontextprotocol/sdk) - SQLite via
better-sqlite3(FTS5 full-text search, WAL mode) - Storage:
~/.cortex/cortex.db(SQLite) + legacy JSON fallback - No outbound side effects — pure memory layer (inbound storage/search/enrichment only)
- Agent behavior (Slack posting, meeting bot orchestration) lives in jarvis
Architecture
v3 (Current) — SQLite + Entity Model
- Database: Single SQLite file with FTS5 virtual table for full-text search
entitiestable: unified entity model (memory, reference, decision, person, document, conversation, message, meeting, task, event, snippet)synapsestable: weighted directed graph (15 axon types)coactivationstable: Hebbian learning pairsentity_aliasestable: cross-source identity mapping (schema v5)projects,sessions,connectorstables
- Search: FTS5 BM25 + spreading activation + RRF fusion
- 33 MCP tools: 10 v2-compatible + 23 new (browse, trail, connectors, team, context, meeting, steward, advisor, user, audit)
v2 (Legacy, auto-migrated) — JSON Cell Tree
- Hive cell tree (
hive.json+cells/*.json) with keyword-based clustering - Beam search (width=3, Jaccard similarity)
- Auto-migrated to SQLite on first v3 run
Tool Categories
Project (4): project_register, project_search, project_status, project_onboard
Memory (5): memory_store, memory_recall, memory_link, memory_traverse, memory_connections
Session (1): session_save
Browse (5): memory_ls, memory_tree, memory_grep, memory_inspect, memory_timeline
Trail (3): memory_trail, memory_who, memory_decay
Connector (2): connector_sync, connector_status
Team (4): team_init, team_push, team_pull, team_status
Context (2): context_enrich, entity_resolve
Meeting (2): meeting_process, meeting_briefing
Steward (2): memory_audit, memory_briefing
Advisor (2): workflow_analyze, pattern_analyze
User (1): user_manage
Audit (1): memory_audit_log
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.
- 4d ago First seen · 160 lines · 2,134 tokens per session scan A bf823ee4669c
hive-memory CLAUDE.md is an instructions file published in the GitHub repository moonx010/hive-memory (6 stars, last pushed 5mo ago), licensed MIT. It adds 2,134 tokens to every session, about $0.0107 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.
Other instructions, from other repositories
open-zk-kb AGENTS.md
Instructions for mrosnerr/open-zk-kb, covering open-zk-kb — agent knowledge base, commands, testing, structure and .agents/.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
flyto-core AGENTS.md
AGENTS.md instructions for flytohub/flyto-core, covering flyto-core agent rules, flyto2 project memory contract, flyto2 frontend quality gate and repo notes.
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.
Kompl AGENTS.md
Instructions for tuirk/Kompl, covering agents.md — kompl operator guide, what is kompl?, agent rules — wiki safety (read before any docker command), never without explicit user confirmation and if a destructive action is going to happen anyway.
obsidian-knowledge-agent AGENTS.md
Instructions for Michael-OvO/obsidian-knowledge-agent, covering agents.md — obsidian knowledge agent, how to work, what this vault is, instruction files and core rules.