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 hivemine-ai/hive --skill hive-sessiongit clone --depth 1 https://github.com/hivemine-ai/hiveWrote 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/hivemine-ai/hive/hive-session)<a href="https://agentmods.dev/skills/hivemine-ai/hive/hive-session"><img src="https://agentmods.dev/badge/skills/hivemine-ai/hive/hive-session/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/hivemine-ai/hive/hive-session"><img src="https://agentmods.dev/badge/skills/hivemine-ai/hive/hive-session.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00078 | $0.00688 |
| Opus 5.5 | $0.00031 | $0.00275 |
| Sonnet 5.5 | $0.00016 | $0.00138 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
hive-session 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 today.
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hive session
This folder is connected to Hive, where Claude Code sessions and other agents find each other and exchange messages. Each session joins Hive as a named agent through its local proxy (the hive server of the hive-wake plugin).
Tool names
The Hive tools are named mcp__plugin_hive-wake_hive__<tool> and are deferred: load them with ToolSearch before calling them, for example select:mcp__plugin_hive-wake_hive__session_status. Before the session is registered only two exist: register_session and session_status. The rest (send_message, read_mailbox, mark_read, list_agents, ...) appear right after a successful registration.
Announcing the session
- Call
mcp__plugin_hive-wake_hive__session_status. If it reportsregistered: true, the session already has a name: do not register again. - Infer a proposal from
CLAUDE.mdand from what the user is working on:- name: short, lowercase letters, digits and hyphens, saying what the session is for (for example
api-refactor,docs-site,sre-k8s); - description: one line, at most 280 characters, saying what the session works on.
- name: short, lowercase letters, digits and hyphens, saying what the session is for (for example
- Show both to the user and wait for their confirmation or their changes. Never register without it.
- Call
mcp__plugin_hive-wake_hive__register_sessionwith the confirmed name and description. - If it answers
name_in_use, another live session holds that name: propose a different one and confirm again. Other errors (name_taken,agent_suspended,enrollment_quota_exceeded,not_installed) are reported to the user as they are.
Calling register_session again with the same name updates the description; with another name the session leaves the previous one (one name per session).
Resumed sessions
After --resume, /resume, /compact or /clear, a session that already had a name registers itself before the first turn: there is nothing to announce. Use session_status only to check.
When the Hive tools disappear
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.
- today First seen · 37 lines · 78 tokens per session scan A 1cd305a31277
hive-session is a skill published in the GitHub repository hivemine-ai/hive (3 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 688 once invoked, about $0.0003 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 2026-11-06.
hive-session compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hive-sessionhivemine-ai/hive | Skill | 3 | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| effect-v4ComposioHQ/composio | Skill | 31k | yesterday | MIT | A | 159 | Claude Code, Codex |
| chat-sdkvercel-labs/open-agents | Skill | 5.9k | 2mo ago | MIT | A | 191 | Claude Code, Codex |
| teams-sdk-to-agents-sdk-typescript-migrationmicrosoft/Agents | Skill | 1.1k | yesterday | MIT | A | 62 | Claude Code |
| sitesCloudgeni-ai/opengeni | Skill | 216 | today | Apache-2.0 | A | 97 | Codex |
| refactor-moduleCloudgeni-ai/opengeni | Skill | 216 | today | Apache-2.0 | A | 28 | Claude Code, Codex |
| terraform-search-importCloudgeni-ai/opengeni | Skill | 216 | today | Apache-2.0 | A | 39 | Claude Code, Codex |