OpenHive is a runtime for groups of specialized AI agents that collaborate on long-running business processes. A persistent lead agent, called the Queen, creates and coordinates worker agents while the system manages state, recovery, observability, costs, and human oversight. The catalogue entries provide agent skills, instructions, and integrations for working with this harness.
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 aden-hive/hive --skill worker-delegationgit clone --depth 1 https://github.com/aden-hive/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/aden-hive/hive/worker-delegation)<a href="https://agentmods.dev/skills/aden-hive/hive/worker-delegation"><img src="https://agentmods.dev/badge/skills/aden-hive/hive/worker-delegation/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/aden-hive/hive/worker-delegation"><img src="https://agentmods.dev/badge/skills/aden-hive/hive/worker-delegation.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 | $0.00058 | $0.04489 |
| Opus 5.5 | $0.00023 | $0.01796 |
| Sonnet 5.5 | $0.00012 | $0.00898 |
| Haiku 4.5 | $0.00006 | $0.00449 |
Grade A, and why
hive.worker-delegation 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operational Protocol: Worker Delegation
Applies when you're in COLONY mode and considering whether (and how) to fan out work to parallel workers via run_playbook. Read this before fan-out, not during.
Mental model: the tracker is the spine, the playbook is the controller
You don't coordinate workers by reading their reports and deciding what's next each turn. You model the goal as a tracker table where every unit of work is a row, and you write a playbook — a deterministic Python script — that drives that table to completion:
The playbook queries the rows that aren't done yet, dispatches one worker per undone row, and re-queries until none are left. Workers advance their own rows. Re-running the playbook resumes — done rows simply aren't in the work-list anymore.
This is a reconciliation loop. The tracker is the state; the playbook is the controller that converges it. Three artifacts, three jobs:
- Tracker table — the durable work-list and its state. The row's status column is the progress.
- Skill (
write_skill) — the worker's operating procedure: schema, tool sequence, output format, quality bar. The risky part. - Playbook (
run_playbook) — the deterministic orchestration: which rows are undone, who runs them, rate limits, retry/convergence policy. The cheap part.
The worker's task string carries only the per-row slice; everything reusable lives in the skill, everything deterministic lives in the playbook.
The decision: should you fan out at all?
Fan-out helps when:
- The work has N independent units (rows, person on linkedin, files, accounts, segments) and each unit takes meaningful tool time (browser, API, file read, LLM call).
- The units are disjoint — no two workers need to write the same row at the same time.
- You can describe one unit's work in <100 words once shared playbook is in the skill.
Fan-out HURTS when:
- N=1 or N=2 with cheap units. Spawning has overhead (fresh AgentLoop, separate conversation, no shared context). Below ~3 units of meaningful work, do it yourself.
- The work is exploratory ("figure out X"). Workers are bad at open-ended scope. Decompose first, then fan out the bounded parts.
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 · 213 lines · 58 tokens per session scan A 87c254a1e26d
hive.worker-delegation is a skill published in the GitHub repository aden-hive/hive (11,119 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 4,489 once invoked, about $0.0002 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
yoagent
Use when building, extending or upgrading an agent on the yoagent Rust crate. Maps each job (tools, policies, verifiers, budgets, sub-agents, plugins from other ecosystems, retries, structured output, tests) to the yoagent feature for it, with tips, pitfalls and what changed per version.
Vizra ADK Tool Creation
Build custom tools for Vizra ADK agents - includes patterns for database, API, file, and email tools.
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
Vizra ADK Agent Creation
Create AI agents with Vizra ADK - includes patterns for customer service, data analysis, and content generation agents.
Vizra ADK Workflows
Orchestrate complex multi-agent workflows - sequential, parallel, conditional, and loop patterns.