Borrowing it
Nothing to install: this file belongs to andreasronge/ptc-fs-mcp. 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/andreasronge/ptc-fs-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/andreasronge/ptc-fs-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/andreasronge/ptc-fs-mcp/agents-md)<a href="https://agentmods.dev/instructions/andreasronge/ptc-fs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/andreasronge/ptc-fs-mcp/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/andreasronge/ptc-fs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/andreasronge/ptc-fs-mcp/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 | $0.00516 | $0.00516 |
| Opus 5 | $0.00258 | $0.00258 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
ptc-fs-mcp 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 8d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guidance
Project overview
ptc-fs-mcp is a small TypeScript filesystem MCP server and library. It exposes
files only beneath one configured root and communicates over stdio. The package
is demo software, but its confinement, cursor integrity, byte budgets, and
protocol behavior are deliberate security and compatibility boundaries.
Setup and commands
- Use a supported Node.js release from
package.json(>=20.19.0) and install the locked dependency tree withpnpm install --frozen-lockfile. This repository uses pnpm, with its exact version pinned inpackage.json. - Run
pnpm run buildto compilesrc/into the ignoreddist/directory. - Run
pnpm testfor the full integration suite. Tests exercise the built CLI over real stdio and create their own temporary filesystem roots. - Run
pnpm run verifybefore proposing a change. It checks formatting and types, rebuilds, and runs the full test suite. - Use
pnpm run formatwhen repository files need Prettier formatting.
Repository conventions
- Keep production code in
src/and tests intest/*.test.mjs. Add or update tests for observable behavior changes and bug fixes. - Do not commit
dist/,node_modules/, coverage output, tarballs, or other generated artifacts. - Preserve ESM imports and the strict TypeScript settings in
tsconfig.json. - Keep stdout reserved for MCP protocol messages. Send diagnostics to stderr, and keep user-facing errors short without stack traces or host paths.
- Keep the server deterministic and self-contained: it must not spawn child processes, access the network, or depend on environment variables.
- Treat path confinement, symlink handling, include/exclude rules, cursor validation, result-size limits, and UTF-8 handling as security-sensitive. Do not weaken them without explicit maintainer direction.
- This server intentionally supports only the MCP protocol profile documented
in
README.md. Do not add negotiation or compatibility fallbacks unless the task explicitly calls for them.
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.
- 8d ago First seen · 47 lines · 516 tokens per session scan A ab167e60406c
ptc-fs-mcp AGENTS.md is an instructions file published in the GitHub repository andreasronge/ptc-fs-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 516 tokens to every session, about $0.0026 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 2026-09-04.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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.
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.
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 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).
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.