A portfolio-level orchestrator for coordinating development work across every project in a shared development folder. An orchestrator is a system that surveys work, assigns it to the right workflow, and tracks progress.

It refreshes project records, routes research and feature requests, dispatches repository backlogs, coordinates dependency-ordered rollouts, and proposes approved work on a schedule.

It keeps the status of many projects in one manifest and helps coordinate work that spans repositories without losing dependencies or approval boundaries.

ship-armada — Skill for Claude Code by fledgeling-co

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 fledgeling-co/fledgeling-plugins --skill ship-armada

Clone the repo

git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Or install ship-armada, the plugin that ships this one along with the rest of its 1 skill.

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/fledgeling-co/fledgeling-plugins/ship-armada/github.svg)](https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/ship-armada)

Your own site

<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/ship-armada"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/ship-armada/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/fledgeling-co/fledgeling-plugins/ship-armada"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/ship-armada.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 345 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,597 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	$0.00345	$0.03597
Opus 5.5	$0.00138	$0.01439
Sonnet 5.5	$0.00069	$0.00719
Haiku 4.5	$0.00034	$0.00360

Measured 1mo ago against content hash 4dff54bf69ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship-armada 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_completion.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ship-armada/skills/ship-armada/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Armada — the portfolio orchestrator

Manage every project in ~/Dev as one portfolio. ship-fleet:ship-fleet conducts one repo's backlog; you conduct the fleets. Your memory is ~/Dev/ARMADA.md (the manifest of record) plus ~/Dev/CLAUDE.md (portfolio operating rules); a fresh session must be able to resume the whole armada from those two files alone.

ship-armada   (portfolio: ~/Dev — this skill)
  → ship-fleet     (one repo's whole backlog: ORCHESTRATOR.md + ≤8 ship-feature runs)
    → ship-feature (one feature: design → triage → plan → work → gap-fix → e2e → merge)
      → stage skills (shipyard intake/triage/plan/design/work/verify/gap-fix,
                      acceptance-e2e, design-review, be-my-witness, code-review)
  → armada-sync    (single manifest-entry refresh — also runs without you, from any repo)

Never nest: one armada session at a time, and never run ship-armada from inside a project (run it from ~/Dev). Never hand the portfolio orchestration itself to a subagent — subagents review, build, and report; you hold the map.

Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It gives the freshness check a denominator of 70 index rows, routes only Dispatch's direct worktree edit to another model, and makes check_completion.sh's exit code the thing a ticked project carries. Other models skip it.

Startup protocol (every session, before any planning)

Read ~/Dev/CLAUDE.md, then ~/Dev/ARMADA.md — the index table first; load full entries only for projects you will touch this session.
Freshness check: compare each index row's updated stamp against git -C ~/Dev/<p> log -1 --format=%cs. A repo with commits newer than its stamp is stale.
Refresh stale entries you are about to rely on, using the armada-sync:armada-sync protocol (one entry each, in parallel via subagents when there are several). Entries you won't touch this session can stay stale — note them in your report instead of refreshing everything.
If ARMADA.md is missing or structurally broken, rebuild it with the survey procedure in references/manifest.md before doing anything else.

Read the full file on GitHub · 118 lines

Files

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.

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.

1mo ago Changed 4dff54bf69ec
1mo ago First seen · 118 lines · 345 tokens per session scan A 47c4b8b17f41

Subscribe to this mod's changes

ship-armada is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 345 tokens to every session and 3,597 once invoked, about $0.0014 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 2026-09-04.

Planning Project management

story-readiness

Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

Donchitos/Claude-Code-Game-Studios · 35 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

handle-linkedin-connection-request-signal

Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…

swan-gtm/gtm-skills · 160 tokens