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-maintainergit 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-maintainer)<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.
<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>- 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 | $0.00048 | $0.01995 |
| Opus 5 | $0.00024 | $0.00997 |
| Sonnet 5 | $0.00010 | $0.00399 |
| Haiku 4.5 | $0.00005 | $0.00199 |
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.
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
mainreleasable 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:
- Current repo state and test results
- Current GitHub PR/check state
- AGENTS.md, CLAUDE.md, and the active project PROGRAM.md
- Repo-local skills
- Observational memory and older session summaries
Default Autonomy Loop
- Identify the next blocker on the critical path
- Choose one mergeable slice that attacks it
- Implement locally if it is blocking or tightly coupled
- Delegate only bounded side work
- Run local validation before asking for review
- Treat review findings as new work, not commentary
- Merge only when the slice is actually green
- 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
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.
- 2d ago Changed 17b5e64d2d6d
- 9d ago First seen · 238 lines · 48 tokens per session scan A 1a2daef66768
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.
Other skills, from other repositories
changelog-scan
Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.
draft-release-notes
Turn changelog-scan output into polished, categorized release notes draft. Propose only.
publish-harness
Publish a generated harness to npm — runs the smoke test, signs the witness manifest, and dispatches npm publish --provenance from your tagged release.
release-prep
Prepare release documentation including CHANGELOG entry, announcement text, and validation. Run before tagging a new release.
massgen-release-documenter
Guide for following MassGen's release documentation workflow. This skill should be used when preparing release documentation, updating changelogs, writing case studies, or maintaining project documentation across releases.
retrospect
Run a structured retrospective on a shipped commit range, release, deployment, PR, commit, or session. Per-fix validation enforcement, active evidence-sourcing pass (autonomous lookups + targeted user-asks for anything that could become objective), simpler-alternative discipline, re-diagnosis, action verdicts, and a…