mcp4openapi CLAUDE.md

Instructions for using lean-ctx, a context tool that reads, searches, and summarizes project files compactly. They define reading modes and a fallback editing method for Claude Code.

In plain words
What is it for?
Use them for file inspection, code searches, directory maps, shell commands, and targeted edits. The instructions explain when to use full content, dependency maps, API signatures, diffs, or specific line ranges.
Why use it?
They help reduce repeated file content and command output in the AI's context. This can make long coding sessions use fewer tokens and provides a clear response to read-dependent edit failures.

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/davidruzicka/mcp4openapi/claude-md
Clone the repo
git clone --depth 1 https://github.com/davidruzicka/mcp4openapi
Per session 313 This file is loaded in full into every session.
When invoked 313 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 $0.00313 $0.00313
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured yesterday against content hash 0d8b95b18d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp4openapi 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 yesterday.

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 · 29 lines

What it actually says

lean-ctx — Context Engineering Layer

PREFER lean-ctx MCP tools over native equivalents for token savings:

PREFER OVER Why
ctx_read(path) Read / cat / head / tail Session caching, 8 compression modes, re-reads cost ~13 tokens
ctx_shell(command) Bash (shell commands) Pattern-based compression for git, npm, cargo, docker, tsc
ctx_search(pattern, path) Grep / rg Compact context, token-efficient results
ctx_tree(path, depth) ls / find Compact directory maps with file counts

ctx_read Modes

  • full — cached read (use for files you will edit)
  • map — deps + API signatures (use for context-only files)
  • signatures — API surface only
  • diff — changed lines only (after edits)
  • aggressive — syntax stripped
  • entropy — Shannon + Jaccard filtering
  • lines:N-M — specific range

File Editing

Use native Edit/StrReplace when available. If Edit requires Read and Read is unavailable, use ctx_edit(path, old_string, new_string) — it reads, replaces, and writes in one MCP call. NEVER loop trying to make Edit work. If it fails, switch to ctx_edit immediately. Write, Delete have no lean-ctx equivalent — use them normally.

Always follow @AGENTS.md

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. yesterday First seen · 29 lines · 313 tokens per session scan A 0d8b95b18d5f

Subscribe to this mod's changes

mcp4openapi CLAUDE.md is an instructions file published in the GitHub repository davidruzicka/mcp4openapi (0 stars, last pushed 15d ago), licensed MIT. It adds 313 tokens to every session, about $0.0016 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.