hive-maintainer

hive-maintainer is a skill for Claude Code, Codex from intertwine/hive-orchestrator. It costs 48 tokens per session (1,995 once invoked), scanned A, original, MIT.

A guide for developers maintaining the Hive software itself. It covers how to split changes, handle reviews, merge work, prepare releases, delegate tasks, and clean up afterward.

In plain words
What is it for?
Planning and shipping Hive repository changes, prioritizing release blockers, preparing fresh worktrees, running checks, responding to review, and leaving useful handoff notes.
Why use it?
It helps keep Hive’s main code line ready to release while work moves through several changes or review cycles. It also explains which checks and sources of truth to trust when information conflicts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Good fit Planning and shipping Hive repository changes, prioritizing release blockers, preparing fresh worktrees, running checks, responding to review, and leaving useful handoff notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/intertwine/hive-orchestrator/hive-maintainer
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.

Any agent
npx skills add intertwine/hive-orchestrator --skill hive-maintainer
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-maintainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/intertwine/hive-orchestrator/hive-maintainer/github.svg)](https://agentmods.dev/skills/intertwine/hive-orchestrator/hive-maintainer)
Your own site
<a href="https://agentmods.dev/skills/intertwine/hive-orchestrator/hive-maintainer"><img src="https://agentmods.dev/badge/skills/intertwine/hive-orchestrator/hive-maintainer/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.

agentmods 80×15 button for hive-maintainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/intertwine/hive-orchestrator/hive-maintainer"><img src="https://agentmods.dev/badge/skills/intertwine/hive-orchestrator/hive-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00048 $0.01995
Opus 5 $0.00024 $0.00997
Sonnet 5 $0.00010 $0.00399
Haiku 4.5 $0.00005 $0.00199

Measured 2d ago against content hash 17b5e64d2d6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hive-maintainer 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 2d 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-maintainer/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hive Maintainer Discipline

Use this skill when you are developing Hive itself, not just using it. It covers the discipline needed for changes that span multiple PRs, subagents, review cycles, or release gates.

Outcomes

  • Keep main releasable at all times
  • Move work forward in highest-value order
  • Use subagents for bounded side lanes only
  • Treat Claude review as part of the implementation loop
  • Leave a compact restart trail after every merge or pause

Ground Truth First

Before substantial work:

make workspace-status
hive doctor --json
uv sync --extra dev

If you are in a fresh maintainer worktree, do the uv sync --extra dev step before running pytest or make check. The focused maintainer/docs suites need the dev-only test dependencies.

Classify current work into:

  • Release blockers — fix these first
  • Mergeable slices — ship these next
  • Follow-up debt — track but do not block on

Prefer the smallest slice that removes a real blocker.

Precedence

When current state, docs, skills, and memory disagree, trust them in this order:

  1. Current repo state and test results
  2. Current GitHub PR/check state
  3. AGENTS.md, CLAUDE.md, and the active project PROGRAM.md
  4. Repo-local skills
  5. Observational memory and older session summaries

Default Autonomy Loop

  1. Identify the next blocker on the critical path
  2. Choose one mergeable slice that attacks it
  3. Implement locally if it is blocking or tightly coupled
  4. Delegate only bounded side work
  5. Run local validation before asking for review
  6. Treat review findings as new work, not commentary
  7. Merge only when the slice is actually green
  8. Record the new head and the next blocker

Do not stall on tiny cleanup once the next real blocker is known. Do not keep adding unrelated work to an already-mergeable PR.

PR Sizing

Prefer one subsystem or one risk cluster per PR.

Warning signs that a PR is too large:

  • Multiple unrelated review themes
  • Difficult-to-summarize purpose
  • Repeated "while I'm here" changes
  • Reviewer confusion about what is actually blocking

Read the full file on GitHub · 238 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. 2d ago Changed 17b5e64d2d6d
  2. 9d ago First seen · 238 lines · 48 tokens per session scan A 1a2daef66768

Subscribe to this mod's changes

hive-maintainer is a skill published in the GitHub repository intertwine/hive-orchestrator (23 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,995 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.