hive-work-loop

hive-work-loop is a skill for Claude Code, Codex from intertwine/hive-orchestrator. It costs 49 tokens per session (1,671 once invoked), scanned A, original, MIT.

A guide to Hive’s standard work cycle for completing governed tasks. It takes an agent from finding available work through claiming, running, monitoring, approval handling, evaluation, and completion.

In plain words
What is it for?
Finding unblocked tasks, building task context, claiming work, launching and monitoring runs, handling approvals, finishing evaluated work, and handing it off cleanly.
Why use it?
It gives agents a repeatable path for working on tasks without skipping ownership, dependency, review, or evaluation steps. Hive is a system that tracks these steps and keeps the result connected to the task.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/intertwine/hive-orchestrator/hive-work-loop
Any agent
npx skills add intertwine/hive-orchestrator --skill hive-work-loop
Clone the repo
git clone --depth 1 https://github.com/intertwine/hive-orchestrator

Made for: Claude Code, Codex.

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.

agentmods badge for hive-work-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/intertwine/hive-orchestrator/hive-work-loop.svg)](https://agentmods.dev/skills/intertwine/hive-orchestrator/hive-work-loop)
Your own site
<a href="https://agentmods.dev/skills/intertwine/hive-orchestrator/hive-work-loop"><img src="https://agentmods.dev/badge/skills/intertwine/hive-orchestrator/hive-work-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01671
Opus 5 $0.00024 $0.00835
Sonnet 5 $0.00010 $0.00334
Haiku 4.5 $0.00005 $0.00167

Measured 5d ago against content hash 2fbe6ea57bce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hive-work-loop 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 5d 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.

skills/hive-work-loop/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hive Work Loop

This is the core cycle for getting work done in Hive. It covers the full path from finding a task to promoting the result.

The Loop

find ready work → build context → claim → launch run → monitor
    → handle approvals → finish (evaluates + promotes) → release

1. Find Ready Work

hive next --json                                    # recommended next task
hive task ready --json                              # full ready queue
hive task ready --project-id <project-id> --json    # scoped to one project

hive next returns the highest-priority unblocked task. It respects dependency constraints and expired claims.

If the queue is empty, check why:

hive deps --json          # shows blockers
hive task list --json     # shows all tasks regardless of status

2. Build Context

hive context startup --project <project-id> --task <task-id> --json

This compiles a startup bundle: task description, acceptance criteria, project mission, API docs, code examples, dependency snapshot, and previous notes.

For a saved markdown bundle (from a repo checkout):

make session PROJECT=<project-id>

3. Claim the Task

hive task claim <task-id> --owner <your-name> --ttl-minutes 30 --json

Claims are time-limited leases. Other agents can see who holds what. Always claim before starting work so you do not collide.

Read PROGRAM.md before proceeding with autonomous work:

cat projects/<project-id>/PROGRAM.md

4. Launch a Run

For governed execution (recommended):

hive work <task-id> --owner <your-name> --json

hive work does several things:

  • Creates a git worktree with an isolated branch
  • Compiles startup context
  • Checkpoints workspace state
  • Launches the driver
  • Emits a run record

For more control over driver and model:

hive work <task-id> --owner <your-name> --driver codex --model gpt-4 --json

For batch mode (no interactive follow-up):

hive run start <task-id> --driver local --json

Read the full file on GitHub · 209 lines

Changes

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.

  1. 5d ago First seen · 209 lines · 49 tokens per session scan A 2fbe6ea57bce

Subscribe to this mod's changes

hive-work-loop is a skill published in the GitHub repository intertwine/hive-orchestrator (23 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,671 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.