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
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/queen-colony-debug)<a href="https://agentmods.dev/skills/aden-hive/hive/queen-colony-debug"><img src="https://agentmods.dev/badge/skills/aden-hive/hive/queen-colony-debug.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 5.1 | $0.00000 | $0.04455 |
| Opus 5 | $0.00000 | $0.02227 |
| Sonnet 5 | $0.00000 | $0.00891 |
| Haiku 4.5 | $0.00000 | $0.00445 |
Grade C, and why
queen-colony-debug scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
If you used `HIVE_HOME=/tmp/hive_e2e`, optionally `rm -rf /tmp/hive_e2e` when done. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
until curl -sf http://127.0.0.1:$PORT/api/health >/dev/null 2>&1; do sleep 1; done How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queen / Colony Debug Skill
SOP for live debugging of queen sessions, colony forks, worker spawns, and tracker DB plumbing without touching the user's production Hive Desktop. Use this when something is wrong in the create_colony → tracker → run_parallel_workers → worker pipeline.
Trigger
User asks you to debug, reproduce, or verify behavior in:
- Queen DM sessions, colony sessions,
fork_session_into_colony ColonyBindingpropagation (queen exec context, workerinput_data)tracker_sql/tracker_register_writable/tracker_upsert/tracker_queryrun_parallel_workerspreflight- Phantom
colonies/session_<uuid>/shadow folders (the original split-brain bug) - Session resume from disk, queen phase transitions (independent → incubating → colony)
Examples: "queen says no such table", "workers can't see what queen wrote", "phantom colony folder appeared", "verify my colony refactor didn't break anything".
Hard rules
- Never run against the user's real Hive Desktop runtime by default. Use an isolated
HIVE_HOME=/tmp/hive_e2efirst. Only switch to the realHIVE_HOME(~/Library/Application Support/Hive/users/<hash>) when the user has explicitly asked for live LLM verification or when an offline repro is impossible. - Never read the real
secrets/,credentials/, orconfiguration.jsondirectories. The auto-mode classifier will block credential exploration. You don't need their contents — the server reads them itself. - Pick a non-default port (
--port 8901/8902/8903) so you don't collide with a running Hive Desktop on8787. - Background the server, don't foreground it.
&redirects the log to a file you cantail/grepwhile you make HTTP calls in parallel. - For "wait for thing X" patterns: use
Bash run_in_background:truewith anuntil grep -q ...loop — never chainsleep N. The harness blocks long leading sleeps. - LLM-driven turns cost real credits. Budget your queen prompts: prefer terse, deterministic instructions ("just call create_colony with these exact args") over open-ended questions.
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 · 332 lines · 0 tokens per session scan C aa7001b1fbe9
queen-colony-debug is a skill published in the GitHub repository aden-hive/hive (11,021 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,455 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
loop-triage
Triage recent CI failures, open issues, and recent commits into a prioritized, actionable picture. Reads the prior STATE.md as memory and rewrites it. The maker half of the loop.
ast-analyzer
Deep Abstract Syntax Tree analysis for understanding code structure, dependencies, impact analysis, and pattern detection at the structural level across multiple programming languages.
validation-standards
Tool usage requirements, failure patterns, consistency checks, and validation methodologies for Claude Code operations.
code-analysis
Provides methodologies, metrics, and best practices for analyzing code structure, complexity, and quality.
diagnose-why-work-stopped
How to handle "why did this work stop / why is this looping?" assignments. Forensics first on the named tree, surface the exact stop-point, frame the fix as a general product rule that respects three invariants (productive work continues, only real blockers stop work, no infinite loops), and deliver a plan — no code…
evidence-collector
Skill "evidence-collector" from aimerdoux/wavex-os, covering qa agent personality, 🧠 your identity & memory, 🔍 your core beliefs, "screenshots don't lie" and "default to finding issues".