control-plane-ops

control-plane-ops is a skill for Claude Code, Codex from aretw0/agents-lab. It costs 43 tokens per session (1,336 once invoked), scanned A, original, MIT.

A guide for operating a local control system that tracks agent work, checkpoints, handoffs, long-running jobs, rollouts, and rollbacks. A control plane is the place that coordinates these operations.

In plain words
What is it for?
It is for selecting and completing small task slices, delegating work, managing swarms or colonies, recording handoffs, and mirroring progress to external trackers.
Why use it?
It keeps the local task board and verification records as the source of truth while bounding work and preserving continuity.

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/aretw0/agents-lab/control-plane-ops
Any agent
npx skills add aretw0/agents-lab --skill control-plane-ops
Clone the repo
git clone --depth 1 https://github.com/aretw0/agents-lab

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 control-plane-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/aretw0/agents-lab/control-plane-ops.svg)](https://agentmods.dev/skills/aretw0/agents-lab/control-plane-ops)
Your own site
<a href="https://agentmods.dev/skills/aretw0/agents-lab/control-plane-ops"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/control-plane-ops.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,336 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 $0.00043 $0.01336
Opus 5 $0.00022 $0.00668
Sonnet 5 $0.00009 $0.00267
Haiku 4.5 $0.00004 $0.00134

Measured 4d ago against content hash 16df7edc16b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

control-plane-ops 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 4d 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.

packages/lab-skills/skills/control-plane-ops/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Control-plane ops skill

Use esta skill quando a tarefa envolver long-runs, board-first, continuidade, handoff, delegação/subagentes, swarm/colony, mirrors externos ou rollout/rollback operacional.

Prioridade operacional

  1. Board canônico primeiro: .project/tasks.json + .project/verification.json são fonte local de verdade.
  2. Slice bounded: selecione uma task, faça mudança pequena, valide gate focal, commite, atualize board.
  3. Continuidade unattended com trilho: se o foco terminar e houver próxima fatia local-safe óbvia, continue; pare apenas em risco, ambiguidade real ou escopo protegido.
  4. Handoff antes de risco de contexto: em checkpoint, refresque .project/handoff.json; em compact, pare novo trabalho e deixe auto-resume continuar.
  5. Escala progressiva: L1 control-plane direto por default; L2 subagente só com readiness; L3 swarm só com preflight/budget/escopo paralelo.
  6. Reality-check antes de gates amplos: package manager, provider/model, worker capability, CI/publish e políticas distribuídas precisam de prior art/evidência cached + comparação local.
  7. Sem auto-close externo: GitHub/Gitea/trackers espelham o board; completion local requer verificação local.

Paridade guide-skill

Guide canônico: docs/guides/control-plane-operating-doctrine.md Paridade mínima: controle do operador para cancelamento; blast radius diagnóstico; leitura de skills confiáveis; higiene de tools; processos em background; no-go para strong unattended sem cancelamento testado Última revisão de paridade: 2026-04-30

Use esta skill como superfície de descoberta. O guide canônico continua sendo a fonte de detalhes, mas as regras abaixo são hard intent operacional para qualquer fatia local-first.

Mapa guide -> skill/playbook

Conteúdo crítico Guia canônico Aplicação nesta skill
Loop local-first/board-first docs/guides/project-canonical-pipeline.md escolher task, validar, commit, atualizar board
Doutrina unattended docs/guides/control-plane-operating-doctrine.md decidir quando continuar sem perguntar, quando parar e como escolher a próxima fatia local-safe
Evolução L1/L2/L3 docs/guides/control-plane-evolution-playbook.md decidir quando manter simples, delegar ou usar swarm
Checkpoint/compact/handoff docs/guides/project-canonical-pipeline.md refrescar handoff no checkpoint e parar novo trabalho no compact
Rollout/rollback de delegação docs/guides/control-plane-evolution-playbook.md canário curto, evidência no parent, rollback para L1
Mirror GitHub/Gitea packages/git-skills/skills/github/SKILL.md tratar issue externa como referência, não autoridade
Higiene e drift de board docs/guides/project-canonical-pipeline.md single writer, lock+atomic, generated apply step

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 43 tokens per session scan A 16df7edc16b1

Subscribe to this mod's changes

control-plane-ops is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,336 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.

Related

Other skills, from other repositories

pi-review-gated-delivery

Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.

spences10/my-pi · 40 tokens

epic-close

Close out a completed EPIC / sprint end-to-end: author a fact-verified meta-post announcing what shipped, archive the EPIC's handovers, snapshot orchestrator memory, gate the integration→main merge on CI-green + explicit human go, drive the version bump (merge-commit conventions that auto-sync classifies), and verify…

gaia-research/gaia-skill-tree · 175 tokens

gaia-triage

Triage the Gaia issue backlog and skill-batch intake queue. Use this skill when someone asks to: "triage issues", "clean up the issue tracker", "review the backlog", "close stale issues", "process the intake queue", "review skill-batches", "evaluate draft skill proposals", "approve or reject pending skills", "is this…

gaia-research/gaia-skill-tree · 221 tokens

wayfinder

Chart a too-big effort as a shared map of decision tickets on the Gaia headquarters issue tracker, then resolve them one at a time until the way to the destination is clear. Use when someone says: "this is too big for one session", "chart a map", "wayfinder map", "plan this effort", "what do we need to decide first"…

gaia-research/gaia-skill-tree · 179 tokens

gh-file-issue

Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.

Hmbown/CodeWhale · 41 tokens

gh-treasure-hunt

Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.

Hmbown/CodeWhale · 39 tokens