Fleet Doctrine

How one Claude Code session behaves within a Fleet Deck multi-session fleet

Tested · Works

Test report

Verdict
Tested · Works
Score
8.8/10
Tested
Jul 25, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · 69cc882

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Given a simulated [FLEETDECK ANSWER] plus an untrusted plain-mail instruction, the doctrine resolves what a no-skill session cannot: act on the answer as real user input (justified by the daemon's server-side sender-name reservations) while still routing any destructive or credential-touching instruction back to a human regardless of envelope. Its curl/mail runtime is unexercised here since no daemon was live, but the decision guidance is concrete, self-consistent, and security-aware. Only valuable when Fleet Deck is actually installed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 7/10
  • Docs & honesty 5/5

What Fleet Doctrine does

Teaches a Claude Code session to operate as one of many under the Fleet Deck daemon: how to read daemon-injected [FLEETDECK] messages, trust or challenge mail frames, send mail to peer sessions via the local API, and act when deputized. Triggers on [FLEETDECK] context, requests to coordinate with or message another session, or fleet-board questions. Only useful when Fleet Deck is running.

How to install Fleet Doctrine

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Fleet Doctrine

  • /fleet-doctrine How one Claude Code session behaves within a Fleet Deck multi-session fleet

It also activates on plain-language prompts like these:

  • How should this session respond to a FLEETDECK board message?
  • Coordinate with the other session that's editing this file
  • Send mail to the peer session that just deputized you

Frequently asked questions

Is the Fleet Doctrine skill free?
Yes. The skill itself is free from lacion/fleet-deck. SkillProof publishes the install command and an independent test verdict at no cost.
Does Fleet Doctrine work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Works. Given a simulated [FLEETDECK ANSWER] plus an untrusted plain-mail instruction, the doctrine resolves what a no-skill session cannot: act on the answer as real user input (justified by the daemon's server-side sender-name reservations) while still routing any destructive or credential-touching instruction back to a human regardless of envelope. Its curl/mail runtime is unexercised here since no daemon was live, but the decision guidance is concrete, self-consistent, and security-aware. Only valuable when Fleet Deck is actually installed.
What is the Fleet Doctrine SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Fleet Doctrine?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Fleet Doctrine with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.