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/yoshiakefasu/mcp-local-files/agents-mdgit clone --depth 1 https://github.com/YoshiaKefasu/mcp-local-filesWrote 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/yoshiakefasu/mcp-local-files/agents-md)<a href="https://agentmods.dev/instructions/yoshiakefasu/mcp-local-files/agents-md"><img src="https://agentmods.dev/badge/instructions/yoshiakefasu/mcp-local-files/agents-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 5.1 | $0.02059 | $0.02059 |
| Opus 5 | $0.01030 | $0.01030 |
| Sonnet 5 | $0.00412 | $0.00412 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
mcp-local-files 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 5d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for Codex and other coding agents working in %USERPROFILE%\mcp-local-files.
Project purpose
This folder contains a minimal local-files MCP server for ChatGPT/Codex. It allows the model to access exactly one local folder through OpenAI Secure MCP Tunnel. The active target folder is read from root-dir.txt by run-mcp.cmd and passed to server.js as ROOT_DIR.
The goal is practical local project assistance: list files, read text files, search text files, write new text files, and safely replace exact text in files.
Important files
server.js Main MCP stdio server. Keep this simple and dependency-light.
cli.js npm CLI wrapper, ROOT_DIR helper, and tunnel-client downloader.
package.json Node package metadata. ESM project, no build step.
run-mcp.cmd Starts server.js with ROOT_DIR loaded from root-dir.txt.
mcp-here.cmd Convenience helper: writes the current terminal directory to root-dir.txt.
root-dir.txt The currently exposed local folder.
README.md User-facing setup and troubleshooting guide.
Current implementation
server.js uses:
@modelcontextprotocol/sdk
zod
Node fs/promises
Node path
StdioServerTransport
cli.js uses only Node built-ins. It starts server.js, updates root files for --tunnel-here, and downloads OpenAI tunnel-client from official release assets on first use.
cli.js setup opens the OpenAI Tunnels and Runtime API keys pages, asks for tunnel_id and the Runtime API key, creates the tunnel-client profile, and stores the key outside this project folder under the user's private config directory.
Registered tools:
list_files
read_file
search_files
stat_file
copy_file
copy_files
write_file
replace_in_file
read_binary_file_base64
write_base64_file
All tool paths are intended to be relative paths inside ROOT_DIR.
Non-negotiable safety rules
Do not expand access beyond ROOT_DIR without explicit user approval.
Do not change the server to accept arbitrary absolute paths.
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.
- 5d ago First seen · 291 lines · 2,059 tokens per session scan A 64e00ce3788f
mcp-local-files AGENTS.md is an instructions file published in the GitHub repository YoshiaKefasu/mcp-local-files (0 stars, last pushed 2mo ago), licensed ISC. It adds 2,059 tokens to every session, about $0.0103 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.
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.
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.
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).