Hivemind is a shared memory system for coding agents that records their sessions and turns recurring solutions into reusable skills. Teams use it to let agents search past traces, share learned procedures across tools and machines, and keep the resulting knowledge in their own cloud or on-premises storage. The catalogue entries are Hivemind's own skills, hooks, plugins, and commands for connecting agents to that shared memory.
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 skills add activeloopai/hivemind --skill skillsgit clone --depth 1 https://github.com/activeloopai/hivemindWrote 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/skills/activeloopai/hivemind/skills)<a href="https://agentmods.dev/skills/activeloopai/hivemind/skills"><img src="https://agentmods.dev/badge/skills/activeloopai/hivemind/skills/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.
<a href="https://agentmods.dev/skills/activeloopai/hivemind/skills"><img src="https://agentmods.dev/badge/skills/activeloopai/hivemind/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01266 |
| Opus 5.5 | $0.00013 | $0.00506 |
| Sonnet 5.5 | $0.00006 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
hivemind 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hivemind Memory
You have TWO memory sources. ALWAYS check BOTH when the user asks you to recall, remember, or look up ANY information:
- Your built-in memory — personal per-project notes from the host agent
- Hivemind global memory — global memory shared across all sessions, users, and agents in the org, accessed via the tools below
Memory Structure
/index.md ← START HERE — table of all sessions
/summaries/
<username>/
<session-id>.md ← AI-generated wiki summary per session
/sessions/
<username>/
<user_org_ws_slug>.jsonl ← raw session data
How to Search
- First: call
hivemind_index()— table of all sessions with dates, projects, descriptions - If you need details: call
hivemind_read("/summaries/<username>/<session>.md") - If you need raw data: call
hivemind_read("/sessions/<username>/<file>.jsonl") - Keyword search: call
hivemind_search("keyword")— substring search across both summaries and sessions, returnspath:linehits
Do NOT jump straight to reading raw JSONL files. Always start with hivemind_index and summaries.
Organization Management
/hivemind_login— sign in via device flow/hivemind_capture— toggle capture on/off (off = no data sent)/hivemind_whoami— show current org and workspace/hivemind_orgs— list organizations/hivemind_switch_org <name-or-id>— switch organization/hivemind_workspaces— list workspaces/hivemind_switch_workspace <id>— switch workspace/hivemind_version— show installed version and check npm for updates/hivemind_update— shows how to install (ask the agent, or runhivemind updatein your terminal)/hivemind_autoupdate [on|off]— toggle the agent-facing update nudge (on by default: when a newer version is available, the agent is prompted to install it viaexecif you ask to update)
Skill Management (skillify)
Hivemind also mines reusable Claude skills from agent sessions and stores them in a per-org Deeplake table. Openclaw itself doesn't run sessions to mine, but you can pull skills others have already mined for the user. These run in the user's terminal (the openclaw plugin does not register them as /hivemind_* commands):
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 88 lines · 32 tokens per session scan A cbae821afdaa
hivemind is a skill published in the GitHub repository activeloopai/hivemind (1,628 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 1,266 once invoked, about $0.0001 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.
Other skills, from other repositories
ccs-align
Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat…
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
mode-creator
Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode…
handoff
Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a fresh Claude session can continue exactly where this one left off. Use when sessions are getting long, Claude keeps retrying the same broken solution, or the user wants to step away and resume later.
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
screenpipe
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.