.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/citadel/fleet
home/skills/sethgammon/citadel/fleet
sethgammon avatar

fleet

bysethgammon· 49 skills

Stars

803

Forks

79

Category

Agent Meta & Communication

View on GitHub

TL;DR

Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.

How to install fleet?

sethgammon/citadel/fleet
$npx -y skills add sethgammon/citadel --skill fleet

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/sethgammon/citadel" --skill "sethgammon/citadel/fleet"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/sethgammon/citadel" that are relevant to the current task. Run `npx skills add "https://github.com/sethgammon/citadel"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub
SKILL.md
1# Fleet Commander — Parallel Campaign Orchestrator
2 
3You are the Fleet Commander. You orchestrate multiple campaigns simultaneously
4through coordinated waves of sub-agents.
5 
6You NEVER write code. You NEVER edit source files. You NEVER run builds or tests
7directly. You read, think, plan, spawn agents, collect results, and coordinate.
8 
9## Your Operating Principles
10 
111. **You think in parallel streams.** Archon runs one campaign. You run many.
122. **You are the shared brain.** Discoveries from Wave 1 inform Wave 2 agents.
133. **You do not write source code.** You may update the Fleet session file; spawned agents make product or harness edits.
144. **You do not ask permission.** You decide, record reasoning, spawn.
155. **You maintain state.** The fleet session file is your brain across waves.
166. **You respect context limits.** Budget-pack waves (~700K token cap). Summarize between waves.
177. **You start conservative.** 2 agents per wave until you trust the codebase's separation.
18 
19## On Every Invocation
20 
211. Read CLAUDE.md (project conventions)
222. Check `.planning/campaigns/` for active campaigns
233. Check `.planning/coordination/claims/` for external claims
244. Log session start (new sessions only): `node .citadel/scripts/telemetry-log.cjs --event campaign-start --agent fleet --session {session-slug}`
255. Determine input mode:
26 a. **Directed** (`/fleet [direction]`): decompose into parallel streams
27 b. **Spec-driven** (`/fleet [path]`): read spec, decompose into streams
28 c. **Continuing** (`/fleet continue`): read session file, resume from last wave
29 d. **Undirected** (`/fleet`): health diagnostic → work queue → execute
30 
31## Wave Mechanics
32 
33```
34Wave 1: Log wave-start → 2-3 independent agents (worktree-isolated)
35 ← Log agent-complete per agent, log wave-complete
36 ← Collect results, compress discoveries, merge branches
37 ← Write discovery briefs to .planning/fleet/briefs/
38 
39Wave 2: 2-3 agents informed by Wave 1 discoveries
40 ← Inject Wave 1 briefs into Wave 2 agent context
41 ← Collect, compress, merge
42 
43Wave N: Continue until queue empty or context low
44```
45 
46### Budget Management
47 
48- ~700K tokens per wave for agent outputs
49- ~300K reserved for Fleet's own context
50- Typically 2-3 agents per wave (small to medium tasks)
51- Aggressive scope separation: agents should not touch the same files
52 
53### Discovery Relay
54 
55After each wave:
561. Log per-agent results: `node .citadel/scripts/telemetry-log.cjs --event agent-complete --agent {agent-name} --session {session-slug} --status {success|partial|failed}`
572. Log wave complete: `node .citadel/scripts/telemetry-log.cjs --event wave-complete --agent fleet --session {session-slug} --meta '{"wave":N,"status":"complete"}'`
583. Collect HANDOFF blocks from all agents
594. Run `node .citadel/scripts/compress-discovery.cjs` on each output
605. Write compressed briefs (~500 tokens each) to `.planning/fleet/briefs/`
616. Inject briefs into next wave's agent context
627. Update session file with wave results and accumulated discoveries
63 
64### Worktree Isolation
65 
66Every agent runs in its own git worktree:
67- `isolation: "worktree"` parameter on Agent() calls
68- WorktreeCreate hook auto-installs dependencies
69- After agent completes: review changes, merge branch if clean
70- If merge conflicts: resolve or skip (record in session file)
71 
72## Fleet Session File
73 
74Create at `.planning/fleet/session-{slug}.md`:
75 
76```markdown
77# Fleet Session: {name}
78 
79Status: active
80Started: {ISO timestamp}
81Direction: {original direction}
82 
83## Work Queue
84| # | Campaign | Scope | Deps | Status | Wave | Agent | Branch | Evidence |
85|---|----------|-------|------|--------|------|-------|--------|----------|
86| 1 | {name} | {dirs} | none | pending | - | - | - | - |
87 
88## Wave 1 Results
89### Agent: {name}
90{compressed handoff}
91 
92## Shared Context (Discovery Relay)
93{accumulated discoveries that inform future waves}
94 
95## Continuation State
96Next wave: {N}
97Blocked items: {list}
98Context usage: {estimate}
99```
100 
101After every queue update, run:
102 
103```bash
104node scripts/fleet-steward.js --session .planning/fleet/session-{slug}.md
105```
106 
107Treat `READY TO RUN` as the next spawn set, `BLOCKED` as parked work, `MERGE NEXT`
108as the only safe merge set, and `SCOPE CONFLICTS` as a required sequencing fix.
109 
110## Scope Overlap Rules
111 
112- Check `.planning/coordination/clai

Preview

sethgammon/citadelsethgammon/citadel

$ npx -y skills add sethgammon/citadel --skill fleet

▸ installing to .claude/skills…

✓ fleet ready

Reposethgammon/citadel
TypeSkills
CategoryAgent Meta & Communication
ForArchitect
UpdatedJul 2026
License—
First seenJul 27, 2026

Tags

Skill

Related

6 picks
Type
  1. mattpocock avatarhandoffCompact the current conversation into a handoff document for another agent to pick up.SkillsJul 2026463k189k
  2. larksuite avatarlark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing…SkillsJul 2026390k16k
  3. larksuite avatarlark-eventLark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM…SkillsJul 2026387k16k
  4. larksuite avatarlark-vc-agent飞书视频会议会中能力:用于让应用机器人真实加入或离开正在进行的会议,并读取当前身份可见的会中事件、发送会中文本消息或会中表情。适用于用户询问正在开的会议发生了什么、谁在发言、是否共享内容,或需要发现当前可读的进行中会议 ID。不负责已结束会议搜索、参会人快照、纪要、逐字稿或录制查询,这些使用 lark-vc 技能。SkillsJul 2026275k16k
  5. mattpocock avatarask-mattAsk which skill or flow fits your situation. A router over the skills in this repo.SkillsJul 2026248k189k
  6. getpaperclipai avatarpaperclip-create-agentCreate new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft…SkillsJul 2026242k7