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/dmongrel/fdx-mcp-server/claude-mdgit clone --depth 1 https://github.com/dmongrel/fdx-mcp-serverWrote 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/dmongrel/fdx-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/dmongrel/fdx-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/dmongrel/fdx-mcp-server/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 | $0.00846 | $0.00846 |
| Opus 5 | $0.00423 | $0.00423 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
fdx-mcp-server 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 — 60 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.
Project overview
fdx-mcp-server is an MCP (Model Context Protocol) server written in TypeScript. The source code repos is at dmongrel/fdx-mcp-server; the main entry point should be index.ts.
The project is Bun-based (primary runtime) but must also run under Deno. All code changes need to be compatible with both runtimes. The MCP server transport type is stdio. This project will start as a tool-by-tool conversion from the Go version, until it gains its own identity.
Go version
The Go implementation of this project lives at /g/_GoProjects/fdx-mcp-server.
| Runtime | Command in .mcp.json |
Notes |
|---|---|---|
| Bun (recommended) | bun run https://raw.githubusercontent.com/dmongrel/fdx-mcp-server/master/index.ts |
Fastest startup; Bun auto-caches the file. |
| Deno | deno run --allow-read --allow-write --allow-net https://raw.githubusercontent.com/dmongrel/fdx-mcp-server/master/index.ts |
Sandboxed by default; flags grant filesystem + network access. |
| Node/NPM (global) | Install with npm install -g fdx-mcp-server, then run as fdx-mcp-server |
Full offline support after one-time install. |
Handoffs
Handoff docs (e.g. *.md describing a bug/feature to pick up in a future session) live at F:\Vault\mcp\fdx-mcp-server, not in this repo. Once a handoff has been implemented, move it into the done\ subfolder there.
Key files
README.md— Setup and configuration instructions for all three runtime pathsCHANGELOG.md— Per-version release notes; update alongside a version bump inpackage.jsonTOOLS.md— Hand-maintained table of every registered tool (name, params, description).idea/— IntelliJ IDEA project metadata (the repo is TypeScript, not a native JetBrains project)
Keeping docs in sync
Any change that adds, removes, renames, or changes the input/output shape of a tool must update
all three of README.md, CHANGELOG.md, and TOOLS.md in the same change — not just the one
that seems most relevant. In practice:
CHANGELOG.mdgets a new version entry (bumppackage.jsonalongside it) describing the change.TOOLS.md's row for that tool (name, parameters, description) is updated to match the tool's actual current schema/description; a removed tool's row is deleted and the tool-count header line is decremented; a new tool gets a new row.README.mdis checked for anything it says about that tool or the feature area — it doesn't enumerate every tool today, so most changes won't touch it, but don't skip the check.- If a tool's own description string changes, check
src/tools/context-data.tsfor a mirrored copy (theget_context/search_actionscatalog) and update it identically — this file is easy to miss since it's not one of the three "docs" above, but drifts the same way.
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 · 60 lines · 846 tokens per session scan A 1e99bed12916
fdx-mcp-server CLAUDE.md is an instructions file published in the GitHub repository dmongrel/fdx-mcp-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 846 tokens to every session, about $0.0042 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-stable apis and released session data, repository layout, commands and host sandbox failures.