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 intertwine/hive-orchestrator --skill hive-coordinationgit clone --depth 1 https://github.com/intertwine/hive-orchestratorWrote 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/intertwine/hive-orchestrator/hive-coordination)<a href="https://agentmods.dev/skills/intertwine/hive-orchestrator/hive-coordination"><img src="https://agentmods.dev/badge/skills/intertwine/hive-orchestrator/hive-coordination.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01276 |
| Opus 5 | $0.00017 | $0.00638 |
| Sonnet 5 | $0.00007 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
hive-coordination 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 8d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hive Coordination
This skill covers how agents work together and how work is orchestrated across projects.
Multi-Agent Task Coordination
Agents coordinate on canonical task state in .hive/tasks/*.md, not on prose or checkboxes.
Core tools
hive task ready --json # what is available
hive task claim <id> --owner <name> --ttl-minutes 30 --json # take a lease
hive task release <id> --json # give it back
hive task link <src> blocked_by <dst> --json # declare dependency
hive deps --json # blocker summary
hive context startup --project <id> --task <id> --json # build context for one task
Pattern: Sequential Handoff
When one task should unlock another:
hive task link <implement-task> blocked_by <research-task> --json
- Agent A claims and completes the research task
- Agent A releases it, marks it done
- The implement task enters the ready queue automatically
- Agent B claims and continues
Pattern: Parallel Independent Work
When several tasks can run simultaneously:
hive task ready --project-id <project-id> --json
Each agent claims a different task. Avoid overlapping file ownership when possible.
Pattern: Review Loop
When work needs evaluator gates:
hive run start <task-id> --json # agent implements
hive run eval <run-id> --json # evaluator checks
hive run accept <run-id> --json # reviewer approves
One agent implements, another reviews artifacts, a human accepts or escalates.
Common Mistakes
- Flipping
ownerin AGENCY.md instead of usinghive task claim - Using checkbox text as the dependency graph instead of task links
- Skipping PROGRAM.md when runs or evaluators are involved
- Leaving long-lived claims after the work is done
Campaigns
Campaigns orchestrate multiple tasks across a project with scheduling and lane-based allocation.
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.
- 8d ago First seen · 190 lines · 35 tokens per session scan A e99b7998578f
hive-coordination is a skill published in the GitHub repository intertwine/hive-orchestrator (23 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,276 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
install-loop
Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
loop-triage
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
issue-triage
Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.
file-a-task
File work into nohuman (taskadd) and check on it (taskstatus) via the nohuman MCP bridge, instead of doing the work inline.
crm-operations
Resolve and safely create/update demo CRM contacts, deals, activity notes and follow-up tasks with revision checks and an atomic audit trail. Use for business-object operations; do not clean spreadsheets, analyze business performance or send customer messages.