file-conversion: Instructions file for Claude Code

CLAUDE.md

file-conversion CLAUDE.md is an instructions file for Claude Code from jmcneil86043/file-conversion. It costs 463 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a file-conversion tool with a reusable library, a command-line interface, and a local assistant service. It documents Markdown-to-Word conversion, including a requirement for the Pandoc program.

In plain words
What is it for?
Use it when working on the file-conversion project, its CLI, its assistant service, or its document-conversion tests.
Why use it?
It gives agents the operating rules needed to use and test the converter correctly across its different interfaces.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jmcneil86043/file-conversion's own configuration. It tells Claude Code how to work on file-conversion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything file-conversion configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jmcneil86043/file-conversion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jmcneil86043/file-conversion/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jmcneil86043/file-conversion

Made for: Claude Code.

Wrote 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.

agentmods badge for file-conversion CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jmcneil86043/file-conversion/claude-md.svg)](https://agentmods.dev/instructions/jmcneil86043/file-conversion/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jmcneil86043/file-conversion/claude-md"><img src="https://agentmods.dev/badge/instructions/jmcneil86043/file-conversion/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 463 This file is loaded in full into every session.
When invoked 463 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00463 $0.00463
Opus 5 $0.00231 $0.00231
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00046 $0.00046

Measured 7d ago against content hash 189ae1fefdd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

file-conversion CLAUDE.md scanned grade A with 1 finding 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 7d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Markdown → Word conversion shells out to `pandoc` (`subprocess.run(['pandoc', ...])`). Pandoc must be installed on the host (`brew install pandoc`). The code raises a clear error if pandoc is missing rather than installi
CLAUDE.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

file-conversion — operating notes

Read this when working inside this project. See requirements/requirements.md for the CLI spec and requirements/mcp.md for the MCP server spec.

Two interfaces, one library

  • Library (file_conversion.core and file_conversion.gxp) — pure functions that take and return file paths. No I/O side effects other than reading inputs and writing outputs. Easy to test in isolation.
  • CLI (.venv/bin/file-conversion) — Click wrapper around the library, for the user and for shell scripts.
  • MCP server (python -m file_conversion.mcp_server) — same library exposed to Claude Desktop. Required because the bash sandbox can't import this project's venv.

All three wrap the same functions. Bug fixes apply once.

System dependency: pandoc

Markdown → Word conversion shells out to pandoc (subprocess.run(['pandoc', ...])). Pandoc must be installed on the host (brew install pandoc). The code raises a clear error if pandoc is missing rather than installing it silently.

GxP template

md_to_docx_gxp does three things beyond the plain converter:

  1. Inserts a version table at the top of the document, populated from YAML frontmatter (versions: list) or empty if absent.
  2. Inserts a definitions table after the version table, populated from frontmatter (definitions: list) or empty if absent.
  3. Sets a footer on every page showing <title> — v<version>, sourced from frontmatter (title:, version:) and overridable via CLI flags.

The frontmatter schema lives in requirements/requirements.md. Keep the parser and the spec in sync — if the schema changes, update both.

Testing before suggesting a Claude Desktop restart

When MCP code changes, smoke-test via the CLI first since both wrap the same library. The CLI requires no restart; the MCP server does.

.venv/bin/pytest                                 # unit tests
.venv/bin/file-conversion csv-to-xlsx a.csv b.xlsx   # CLI smoke

Only suggest a Claude Desktop restart after the CLI confirms the change works.

Read the full file on GitHub · 37 lines

Changes

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.

  1. 7d ago First seen · 37 lines · 463 tokens per session scan A 189ae1fefdd5

Subscribe to this mod's changes

file-conversion CLAUDE.md is an instructions file published in the GitHub repository jmcneil86043/file-conversion (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 463 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens