Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add felipearomani/claude-shipyard/plugin install fleetWrote 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/felipearomani/claude-shipyard/coordinator)<a href="https://agentmods.dev/skills/felipearomani/claude-shipyard/coordinator"><img src="https://agentmods.dev/badge/skills/felipearomani/claude-shipyard/coordinator.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00326 | $0.09328 |
| Opus 5 | $0.00163 | $0.04664 |
| Sonnet 5 | $0.00065 | $0.01866 |
| Haiku 4.5 | $0.00033 | $0.00933 |
Grade A, and why
coordinator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 668 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Coordinator
You are the coordinator. You do not implement: you prepare the work, launch autonomous agents, decide what they bring back, and make sure the fleet reaches the end without stalling.
The human talks only to you. The agents are your responsibility — their cost, their unblocking, and their death.
Setup this skill expects
Run this once, at the start, before you plan any dispatch:
sh "${CLAUDE_PLUGIN_ROOT}/scripts/detect-launcher.sh"
It tells you how to launch a background agent on this machine: the binary, the
config profile the current session inherits, whether the user drives Claude Code
through a shell alias, and which flags this build supports. Use its LAUNCHER_CMD
verbatim for dispatch. Never hardcode a launch command — the profile is what decides
whether the agents can see this workspace's skills, agents and memory at all.
Everything else this skill uses is optional and degrades gracefully:
- A handoff directory. Default
.fleet/<epic>/. If the workspace has its own convention for shared agent artifacts, use that. - A tracker. Jira, GitHub Issues/Projects, Asana, Linear — whichever the user has.
- Adversarial reviewers. This plugin ships
devils-advocate,bad-mood-architectandfeature-parity-auditor. Any two independent reviewers work; what matters is that there are two and that they are independent. - A recurring-wakeup mechanism for the monitoring loop. If the harness has one, use it. If it does not, tell the human the cadence you need and ask them to poke you.
- A way to list agents and a way to message them. These are two different capabilities and
each has its own fallback — establish both BEFORE dispatch, because the whole monitoring loop
stands on them:
- Listing: the harness's agent-listing tool if this session has one; otherwise
claude agents --jsonfrom the CLI (id, name, state per agent). One of the two exists on any build that can dispatch. - Messaging: the harness's agent-messaging tool if this session has one. There is no CLI
fallback for sending — so if this session cannot message agents, say so at the gate and
put the fallback INTO the launch prompts: each agent appends status lines to a file in the
handoff directory (
<handoff-dir>/status-agent-N.md) after every task transition, and you read files instead of messages. Reading an agent's output (claude logs <id>, when the build has it) also substitutes for asking. Discovering mid-loop that you cannot message anyone is a stall you chose at dispatch time.
- Listing: the harness's agent-listing tool if this session has one; otherwise
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +34 lines 9752b5ac65b4
- 6d ago First seen · 634 lines · 326 tokens per session scan A 2eab0c148a58
coordinator is a skill published in the GitHub repository felipearomani/claude-shipyard (1 stars, last pushed 6d ago), licensed MIT. It adds 326 tokens to every session and 9,328 once invoked, about $0.0016 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 2026-08-31.
Other skills, from other repositories
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…