fleetline: Instructions file for Claude Code

CLAUDE.md

fleetline CLAUDE.md is an instructions file for Claude Code from ClaudeTool/fleetline. It costs 4,646 tokens per session, scanned E, original, MIT.

A project handoff document for fleetline, a Claude Code statusline plugin. It explains the project's purpose, distribution methods, file layout, non-obvious details, and remaining work so a new coding session can continue it.

In plain words
What is it for?
Use it as a reference before changing fleetline, especially to understand its plugin marketplace package, standalone installer, files, limitations, and open tasks.
Why use it?
It preserves project context that would otherwise be lost between sessions or contributors. This helps prevent incorrect edits and makes unfinished work easier to pick up.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is ClaudeTool/fleetline's own configuration. It tells Claude Code how to work on fleetline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fleetline configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to ClaudeTool/fleetline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ClaudeTool/fleetline/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ClaudeTool/fleetline

Made for: Claude Code.

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.

agentmods badge for fleetline CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/claudetool/fleetline/claude-md/github.svg)](https://agentmods.dev/instructions/claudetool/fleetline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/claudetool/fleetline/claude-md"><img src="https://agentmods.dev/badge/instructions/claudetool/fleetline/claude-md/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.

agentmods 80×15 button for fleetline CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/claudetool/fleetline/claude-md"><img src="https://agentmods.dev/badge/instructions/claudetool/fleetline/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,646 This file is loaded in full into every session.
When invoked 4,646 The same file — it is already loaded in full.
Security scan E 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04646 $0.04646
Opus 5.5 $0.01858 $0.01858
Sonnet 5.5 $0.00929 $0.00929
Haiku 4.5 $0.00465 $0.00465

Measured 1mo ago against content hash 328f23a68fa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade E, and why

fleetline CLAUDE.md scanned grade E with 3 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.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

The local-file test above doesn't catch everything: `curl | bash` behaves

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$TESTHOME"; mkdir -p "$TESTHOME"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

standalone `install.sh` (curl-installable, no marketplace needed, but
CLAUDE.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fleetline — project context for Claude

This file exists so a fresh Claude Code session (different machine, no memory of the original conversation) can pick this project back up with full context. Read this before touching any code here.

What this is

A Claude Code statusline plugin, distributed two ways: the plugin marketplace (.claude-plugin/plugin.json + commands/statusline-setup.md does the setup interview and writes config/settings.json) and a standalone install.sh (curl-installable, no marketplace needed, but missing the hook-based and fleet-view features — see below).

Originally started as the user's own personal statusline script (~/.claude/statusline-command.sh), shared informally as a one-file installer. This repo is that script turned into a proper, hardened, shareable plugin — first named claude-statusline, renamed to fleetline after discovering the original name was already taken by an unrelated project (verified via web search: felipeelias.github.io blog post, plus ccstatusline/starship-claude/cship/ccsidekick/ codachi already crowding the space).

File map

.claude-plugin/plugin.json    plugin manifest (name, version, description)
bin/lib.sh                    shared helpers — colors, sanitize(), cfg_bool(),
                               draw_bar()/rate_bar(), fit_line() (width-aware
                               truncation), OSC-8 link builders. Sourced by
                               both scripts below; not executed directly.
bin/statusline.sh             the main statusLine renderer (1-N lines, no
                               fixed count). Every piece is computed into a
                               *_SEG/*_PART variable, looked up by id via
                               segment_value(). Lines come from either the
                               layout's built-in default (3 fixed presets) or
                               the config's `segments` override — a FLAT
                               ordered id array with a reserved "newline" id
                               to break lines, modeled after powerlevel10k's
                               POWERLEVEL9K_LEFT_PROMPT_ELEMENTS — see
                               "Custom segment order" in README.md. The
                               separator glyph between segments is also
                               config-driven (`separator.preset`/`.custom`).
bin/subagent-statusline.sh    the subagentStatusLine renderer (fleet/agent
                               panel view) — LEAST-VERIFIED file, see below
hooks/hooks.json + agent-count.sh   optional SubagentStart/Stop counter,
                               plugin-only (see "Open questions")
config/schema.json            documents every config field + default
commands/statusline-setup.md  the /statusline-setup interview + settings.json
                               writer (with backup-before-overwrite)
install.sh                    curl-installable single-file build — bin/lib.sh
                               is INLINED into it (regenerate if you edit
                               lib.sh or statusline.sh — see below). Also owns
                               its own version tracking: `INSTALLER_VERSION`
                               at the top, written to
                               `~/.claude/statusline-fleetline.version` on
                               every successful install, read back by its
                               `--check-update` flag (report-only, no GitHub
                               API — see "Updating" in README.md). This logic
                               lives in install.sh's own header/footer, OUTSIDE
                               the inlined STATUSLINE_EOF block, so it does
                               NOT require the regen recipe below.
docs/index.html               GitHub Pages landing page (self-contained,
                               dark-only by deliberate choice, no build step)
README.md                     user-facing docs (install, config, limitations)

Read the full file on GitHub · 332 lines

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.

  1. 1mo ago Changed · +64 lines · +919 tokens per session scan A → E 328f23a68fa7
  2. 2mo ago First seen · 268 lines · 3,727 tokens per session scan A 5eb604ad12c3

Subscribe to this mod's changes

fleetline CLAUDE.md is an instructions file published in the GitHub repository ClaudeTool/fleetline (4 stars, last pushed 1mo ago), licensed MIT. It adds 4,646 tokens to every session, about $0.0186 per session on Opus 5.5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens