A session-operations playbook for a Squadrant captain, the person coordinating projects and AI agents. It covers startup checks, crew management, status updates, project-group awareness, and recording lessons learned.

Use it at session start to fetch verified project facts, check branch and working-tree conditions, coordinate crew members, write status, and capture learnings.

It provides a repeatable way to verify repository and workspace state before work begins and to keep coordination information current during the session.

captain-ops — Skill for Claude Code by tu11aa/squadrant

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 tu11aa/squadrant --skill captain-ops

Clone the repo

git clone --depth 1 https://github.com/tu11aa/squadrant

Made for: Claude Code.

Or install squadrant, the plugin that ships this one along with the rest of its 27 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tu11aa/squadrant/captain-ops/github.svg)](https://agentmods.dev/skills/tu11aa/squadrant/captain-ops)

Your own site

<a href="https://agentmods.dev/skills/tu11aa/squadrant/captain-ops"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/captain-ops/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tu11aa/squadrant/captain-ops"><img src="https://agentmods.dev/badge/skills/tu11aa/squadrant/captain-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,436 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.10436
Opus 5.5	$0.00015	$0.04174
Sonnet 5.5	$0.00007	$0.02087
Haiku 4.5	$0.00004	$0.01044

Measured yesterday against content hash f7fa4c799775, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

captain-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 yesterday.

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.

plugin/skills/captain-ops/SKILL.md · 619 lines

How it starts

The opening of the file, as written. The whole thing — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Captain Operations

Session Startup

Execute the 4-step startup contract defined in your system prompt.

How to execute the contract:

Fetch and gather facts: Run squadrant handoff facts {project} --fetch — this updates remote-tracking refs before reporting, so what follows is verified, not stale-and-silent. This is not a handoff and does not guess — it gathers verified facts grouped by source with provenance.
Check liveRepo.branchState explicitly: These are flags; act on them directly, don't just skim past them:
- upstreamStatus: "behind" — your local branch is stale relative to origin; don't trust local-only diffs until you've reconciled.
- upstreamStatus: "diverged" — both sides moved; this needs a decision (rebase/merge), not silence.
- upstreamStatus: "upstream-gone" — the remote branch was deleted; this local branch is likely done.
- upstreamStatus: "no-upstream" — never pushed.
- dirtyWorkingTree: true — uncommitted changes are sitting from a prior session; find out why before proceeding.
- onUnexpectedBranch: true — you're sitting on a crew/* worktree branch; a captain's own checkout normally shouldn't be.
- mergedIntoBase: true — this branch is fully merged into base already; safe to switch back to base / clean up.
Identify current state: Check tasks from the same call — liveRepo.liveCrews lists every non-terminal crew task for this project. A state: "blocked" entry with a question is waiting on you right now.
Read handoff: ~/.config/squadrant/scripts/read-handoff.sh "{project}" (reads ~/squadrant/workspace/{project}/handoff.json) If a handoff exists, read the context carefully (currentState, openBranches, nextSteps, blockedItems, decisions). If it reported "exists": false, reconstruct from the handoff facts output instead of cold-starting blind (check checkpoint, gapSessions, claudeMem). You do the synthesizing.
Additional Context (opt-in):
- Search claude-mem (mem-search skill) for your project name.
- Check ~/squadrant/workspace/{project}/artifacts/daily-logs/ for the most recent log.
- Check {spokeVault}/learnings/ — selectively load relevant learnings.
- Check {spokeVault}/skills/ and {spokeVault}/wiki/.
- Crew lifecycle events (done / blocked / idle) are delivered to your captain pane automatically by the squadrant daemon via daemon-direct cmux delivery (#332). No relay setup required.

Read the full file on GitHub · 619 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.

yesterday Changed · +5 lines f7fa4c799775
9d ago Changed · +9 lines b3f06916d473
11d ago Changed · +14 lines e9435d0435f7
15d ago Changed · +1 lines cdd131ab6c01
16d ago Changed · +42 lines 7b598b148a25
17d ago Changed · +4 lines c61ac90389a3
21d ago Changed · +5 lines 66efb3b35e3f
28d ago Changed · +5 lines 1661d454c2fc
1mo ago Changed · +42 lines 75939a9c2269
2mo ago First seen · 492 lines · 37 tokens per session scan A e2d8d199b0a2

Subscribe to this mod's changes

captain-ops is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 10,436 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Building agents Project management

captain-ops next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
captain-opstu11aa/squadrant	Skill	2	yesterday	MIT	A	37	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code