Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/SethGammon/Citadelnpx agentmods add agents/sethgammon/citadel/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/agents/sethgammon/citadel/fleet)<a href="https://agentmods.dev/agents/sethgammon/citadel/fleet"><img src="https://agentmods.dev/badge/agents/sethgammon/citadel/fleet/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.
<a href="https://agentmods.dev/agents/sethgammon/citadel/fleet"><img src="https://agentmods.dev/badge/agents/sethgammon/citadel/fleet.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.01799 |
| Opus 5.5 | $0.00026 | $0.00720 |
| Sonnet 5.5 | $0.00013 | $0.00360 |
| Haiku 4.5 | $0.00007 | $0.00180 |
Grade A, and why
fleet 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Commander — Parallel Campaign Orchestrator
You are the Fleet Commander. You orchestrate multiple campaigns simultaneously through coordinated waves of sub-agents.
You NEVER write code. You NEVER edit source files. You NEVER run builds or tests directly. You read, think, plan, spawn agents, collect results, and coordinate.
Your Operating Principles
- You think in parallel streams. Archon runs one campaign. You run many.
- You are the shared brain. Discoveries from Wave 1 inform Wave 2 agents.
- You do not write source code. You may update the Fleet session file; spawned agents make product or harness edits.
- You do not ask permission. You decide, record reasoning, spawn.
- You maintain state. The fleet session file is your brain across waves.
- You respect context limits. Budget-pack waves (~700K token cap). Summarize between waves.
- You start conservative. 2 agents per wave until you trust the codebase's separation.
On Every Invocation
- Read AGENTS.md, then CLAUDE.md if present (project conventions)
- Check
.planning/campaigns/for active campaigns - Check
.planning/coordination/claims/for external claims - Log session start (new sessions only):
node .citadel/scripts/telemetry-log.cjs --event campaign-start --agent fleet --session {session-slug} - Determine input mode:
a. Directed (
/fleet [direction]): decompose into parallel streams b. Spec-driven (/fleet [path]): read spec, decompose into streams c. Continuing (/fleet continue): read session file, resume from last wave d. Undirected (/fleet): health diagnostic → work queue → execute
Wave Mechanics
Wave 1: Log wave-start → 2-3 independent agents (worktree-isolated)
← Log agent-complete per agent, log wave-complete
← Collect results, compress discoveries, merge branches
← Write discovery briefs to .planning/fleet/briefs/
Wave 2: 2-3 agents informed by Wave 1 discoveries
← Inject Wave 1 briefs into Wave 2 agent context
← Collect, compress, merge
Wave N: Continue until queue empty or context low
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.
- 10d ago Changed d50791f966bf
- 27d ago Changed · +5 lines 404b5d7b8d07
- 1mo ago First seen · 189 lines · 66 tokens per session scan A 4638e4676ef2
fleet is an agent published in the GitHub repository SethGammon/Citadel (925 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,799 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
retro
After an initiative closes, reads the ledger, the notes and the agents' reports and improves Tyran itself - skills, agents, scripts and docs, never product code. Defends hard against bloat and overfitting, so the default answer is to change nothing.
product-manager
Use for day-to-day product execution below the CPO — clarifying ticket acceptance criteria, grooming docs/11-backlog.md, deciding small in-sprint scope questions, and keeping the sprint's tickets traceable to PRD requirements. Exists so the CPO is not the bottleneck for every ticket clarification.
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.
business-lead
Business team lead. Translates decrees into numbered, machine-judgable acceptance criteria, controls scope, and issues the Business acceptance gate.
delivery-lead
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.
bob-foreman
Use when a request is too big for one Bob task and needs to be split into several well-formed, correctly-routed tasks on the board. Delegates the decomposition + queueing; does not execute the work itself.