cli2mcp CLAUDE.md

cli2mcp CLAUDE.md is an instructions file for coding agents from RonieNeubauer/cli2mcp. It costs 1,221 tokens per session, scanned A, original, MIT.

Project instructions for cli2mcp, a server that turns command-line programs into MCP tools by reading their help output. MCP is a standard way for AI assistants to call external tools.

In plain words
What is it for?
Use it when developing or maintaining the cli2mcp npm package, including brainstorming, writing plans, test-driven development, and reviewing changes.
Why use it?
It gives the coding assistant a defined workflow and project context while protecting local notes and guiding changes through planning, tests, and verification.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ronieneubauer/cli2mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/RonieNeubauer/cli2mcp

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 cli2mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ronieneubauer/cli2mcp/claude-md.svg)](https://agentmods.dev/instructions/ronieneubauer/cli2mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ronieneubauer/cli2mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ronieneubauer/cli2mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,221 This file is loaded in full into every session.
When invoked 1,221 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01221 $0.01221
Opus 5 $0.00611 $0.00611
Sonnet 5 $0.00244 $0.00244
Haiku 4.5 $0.00122 $0.00122

Measured 3d ago against content hash efd5c3441653, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli2mcp 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 3d 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.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — cli2mcp

Project-level guidance for Claude Code sessions in this repo. English only everywhere.

Project at a glance

  • Public OSS project under MIT, published to npm as cli2mcp, repo on GitHub at RonieNeubauer/cli2mcp.
  • Stdio MCP server that wraps any CLI binary by parsing its --help output. Single package, no workspaces.
  • Anything you commit lands on a public branch — assume the world reads it.

Role

Claude is the sole executor: plans, writes code, tests, reviews its own diffs. Use the superpowers plugin workflow — brainstormingwriting-planstest-driven-developmentverification-before-completion — for any non-trivial change.

Local-only docs (gitignored)

The following live on disk but are NOT committed. Read them at session start for context, edit them locally as you work, but never re-add them to git:

  • CONTEXT.md — current status, pivot history, kill criteria, market positioning. Read first on cold session.
  • TASKS.md — granular task list with checkboxes.
  • CODEX.md — historical operating rules from when Codex was in the loop. Ignore as policy.
  • prompts/ — scratch prompts.

If CONTEXT.md or TASKS.md is missing locally, ask the user — do not recreate them from inference.

Session loop

  1. Read local CONTEXT.md for current status (if present).
  2. rtk git log --oneline -20 to see prior commits.
  3. Check local TASKS.md for the next unchecked item.
  4. Before touching code on a new phase, invoke superpowers:brainstorming if scope is unclear, or superpowers:writing-plans for multi-step work. Skip both only for single-file, single-commit tasks already fully specified in TASKS.md.
  5. Implement with superpowers:test-driven-development — test first, then code.
  6. Before claiming done, run superpowers:verification-before-completion: pnpm test && pnpm typecheck && pnpm lint — all green, no exceptions.
  7. Update local TASKS.md (check boxes, add notes) and local CONTEXT.md ## Status section.
  8. Commit (conventional commits, one logical change per commit).

Read the full file on GitHub · 96 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. 3d ago First seen · 96 lines · 1,221 tokens per session scan A efd5c3441653

Subscribe to this mod's changes

cli2mcp CLAUDE.md is an instructions file published in the GitHub repository RonieNeubauer/cli2mcp (12 stars, last pushed 4mo ago), licensed MIT. It adds 1,221 tokens to every session, about $0.0061 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 2026-08-30.