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.
npx agentmods add instructions/nicknisi/fleet/claude-mdgit clone --depth 1 https://github.com/nicknisi/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/instructions/nicknisi/fleet/claude-md)<a href="https://agentmods.dev/instructions/nicknisi/fleet/claude-md"><img src="https://agentmods.dev/badge/instructions/nicknisi/fleet/claude-md.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 | $0.00183 | $0.00183 |
| Opus 5 | $0.00092 | $0.00092 |
| Sonnet 5 | $0.00037 | $0.00037 |
| Haiku 4.5 | $0.00018 | $0.00018 |
Grade A, and why
fleet CLAUDE.md 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 4d 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.
What it actually says
Fleet
Agent dashboard TUI for managing AI agent sessions in tmux. Also a Claude Code plugin for hook auto-discovery.
Architecture
Bash hooks write state → Bun TUI reads state. Three-layer state engine: hook signals, JSONL event stream, pane scraping.
Development
- Runtime: Bun
- Build:
bun run build(compiles to standalone binary) - Test:
bun test - Lint:
bun run lint - Format:
bun run format - Typecheck:
bun run typecheck - Dev:
bun run dev(runs without compiling)
Conventions
- Zero runtime dependencies
- TypeScript strict mode with noUncheckedIndexedAccess
- Collocated tests:
*.test.tsnext to source - Raw ANSI rendering (no TUI framework)
- Single-string-per-frame rendering (no flicker)
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.
- 4d ago First seen · 26 lines · 183 tokens per session scan A 642a7811f02d
fleet CLAUDE.md is an instructions file published in the GitHub repository nicknisi/fleet (24 stars, last pushed 7d ago), licensed MIT. It adds 183 tokens to every session, about $0.0009 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 2026-08-30.
Other instructions, from other repositories
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
luvus AGENTS.md
AGENTS.md instructions for RizRiyz/luvus, covering agents.md, start with current evidence, product model, non-negotiable development safety and architecture and code map.
tmuxy CLAUDE.md
Claude Code instructions for flplima/tmuxy, covering tmuxy, project structure, cli usage, pane operations and tab operations.
vnx-orchestration CLAUDE.md
Claude Code instructions for Vinix24/vnx-orchestration, covering vnx governance, mandatory report contract, dispatch lanes, path resolution and event streams.
CommandMate CLAUDE.md
Claude Code instructions for Kewton/CommandMate, covering claude.md, ⚠️ 重要: モジュール詳細を claude.md に書かないこと, プロジェクト概要, 基本情報 and 技術スタック.
operator CLAUDE.md
Claude Code instructions for untra/operator, covering claude.md - operator, project overview, tech stack, code style and plans & specs location.