Borrowing it
Nothing to install: this file belongs to andre-motta/claude-fleet-monitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andre-motta/claude-fleet-monitor/main/AGENTS.mdgit clone --depth 1 https://github.com/andre-motta/claude-fleet-monitorWrote 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/andre-motta/claude-fleet-monitor/agents-md)<a href="https://agentmods.dev/instructions/andre-motta/claude-fleet-monitor/agents-md"><img src="https://agentmods.dev/badge/instructions/andre-motta/claude-fleet-monitor/agents-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.
<a href="https://agentmods.dev/instructions/andre-motta/claude-fleet-monitor/agents-md"><img src="https://agentmods.dev/badge/instructions/andre-motta/claude-fleet-monitor/agents-md.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 | $0.00885 | $0.00885 |
| Opus 5.5 | $0.00354 | $0.00354 |
| Sonnet 5.5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
claude-fleet-monitor AGENTS.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 2mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Contributing Guide
Guidelines for AI agents (Claude Code, Copilot, etc.) contributing to this repository.
Agent SDLC
Use docs/SDLC.md for substantial initiatives and explicit workflow requests. Astra leads architecture/orchestration; Sol at high handles senior work and independent review; Luna at xhigh handles bounded work under Sol review. Use actual runtime models, isolated worktrees and autonomous signed-off local commits within approved scope. Follow the CTO-approved issue-level feature-branch PR gates in the profile; Astra owns child merges, and final main merge remains the CTO gate. The profile records the adoption authorization, workflow baseline, checks and instruction reconciliation. Preserve unrelated rules below.
Before You Start
- Read
CLAUDE.mdfor architecture and design decisions. - Run
pytestto confirm the test suite passes before making changes. - Check existing issues and PRs to avoid duplicate work.
Making Changes
- Write tests for new functionality. Tests live in
tests/and use pytest withtmp_pathfixtures. - Keep changes cross-platform. Never assume Linux (
/proc,pgrep). Usesys.platformchecks and the abstractions indiscovery.py. - Shared process discovery and session filesystem access go through
discovery.py. The hook owns fleet event writes, CLI install/uninstall owns harness configuration, and terminal APIs own terminal integration. Do not duplicate platform-specific discovery logic in consumers. - The hook (
hook.py) must stay fast. No heavy imports at module level, no network calls.
Terminal APIs
- Focus logic goes through
focus.py, which delegates to terminal APIs interminal_apis/. - Each terminal emulator has its own module implementing
TerminalAPI(seeterminal_apis/base.py). - To add a new terminal: create
terminal_apis/newterminal.py, implement the ABC, add toTERMINALSlist interminal_apis/__init__.py, add detection env var toTERMINAL_PROCESS_NAMESintmux.pyfor nested terminal support. - Terminal detection happens at hook time via env vars, not at focus time. Each session stores its
terminalandterminal_envin the fleet JSON. - For multiplexers (tmux, zellij) that run inside other terminals,
raise_window()must detect the parent terminal via process tree walking and chain to its API.
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.
- 2mo ago Changed · +11 lines · +182 tokens per session fba038c682ed
- 2mo ago First seen · 59 lines · 703 tokens per session scan A df30552956c1
claude-fleet-monitor AGENTS.md is an instructions file published in the GitHub repository andre-motta/claude-fleet-monitor (2 stars, last pushed 3d ago), licensed MIT. It adds 885 tokens to every session, about $0.0035 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 2026-08-31.
claude-fleet-monitor AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-fleet-monitor AGENTS.mdandre-motta/claude-fleet-monitor | Instructions file | 2 | 3d ago | MIT | A | 885 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |