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/imateo/fastpanel-mcp/claude-mdgit clone --depth 1 https://github.com/iMateo/fastpanel-mcpWrote 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/imateo/fastpanel-mcp/claude-md)<a href="https://agentmods.dev/instructions/imateo/fastpanel-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/imateo/fastpanel-mcp/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 | $0.02488 | $0.02488 |
| Opus 5 | $0.01244 | $0.01244 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
fastpanel-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
An MCP (Model Context Protocol) server that exposes a FastPanel 2 hosting panel's REST API as tools. It runs over stdio and is consumed by Claude Code, Claude Desktop, Cursor, etc. The entire server is ~850 lines across four src/ files.
Commands
pnpm build # tsc → dist/ (the published artifact; bin is dist/index.js)
pnpm typecheck # tsc --noEmit — run this to validate changes; there is no test suite
pnpm dev # tsx watch src/index.ts — hot-reload for local iteration
pnpm inspect # MCP Inspector GUI against dist/index.js
pnpm start # node dist/index.js
There are no unit tests and no linter. The only runtime check is scripts/smoke.mjs, which spawns the built server, runs initialize → tools/list, and calls the read tools against a live panel:
FASTPANEL_URL=… FASTPANEL_TOKEN=… node scripts/smoke.mjs
Always pnpm build before running smoke or inspect — they execute dist/, not src/.
Architecture
Four layers, registered in index.ts:main():
config.ts—loadConfig()reads env (FASTPANEL_URL,FASTPANEL_TOKEN, optionalFASTPANEL_WRITE_TOKEN,FASTPANEL_INSECURE_TLS,FASTPANEL_TIMEOUT_MS, and the optionalFASTPANEL_SSH_*block) and throws on missing required vars. The dual-token split lives here:writeTokenisnullwhen unset;sshisnulluntilFASTPANEL_SSH_HOSTis set.client.ts—FastPanelClientwrapsundiciwith one persistentAgent.get()uses the read token;post/patch/put/delete()setrequiresWrite:trueand use the write token, throwingFastPanelWriteDisabledErrorif it's null.>=400responses throwFastPanelErrorcarrying status + parsed body.ssh.ts—SshClientshells out to the operator's ownssh(viaexecFile, no library dep, no local shell) to run commands on the panel host. Opt-in and host-agnostic — nothing about a specific server is baked in; host/user/port/key all come fromFASTPANEL_SSH_*.exec()resolves with stdout/stderr/exit code (does not throw on non-zero, so callers can read e.g.nginx -tfailures); throwsSshDisabledErrorwhen SSH is unconfigured.upload()pushes a local file/dir withrsync(scp fallback if local rsync is missing;--deleteis rsync-only) andputContent()streams an inline buffer into a remote file viacatoverspawn— both reuse the same connection options asexec()and never route bytes through the model for the rsync path. Dynamic values interpolated into remote commands MUST go throughshq().tools.ts—registerTools(server, client, ssh)registers every tool. This is where all FastPanel API knowledge lives.
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 · 82 lines · 2,488 tokens per session scan A fb64d709fba2
fastpanel-mcp CLAUDE.md is an instructions file published in the GitHub repository iMateo/fastpanel-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,488 tokens to every session, about $0.0124 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 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.