agentmods.dev

recipe-tools CLAUDE.md

recipe-tools CLAUDE.md is an instructions file for coding agents from lka/recipe-tools. It costs 550 tokens per session, scanned A, original, MIT.

Project instructions for recipe-tools, a Python service whose tools handle image-selection work. They describe its architecture, shared utilities, working-directory setting, and development conventions.

In plain words
What is it for?
Use them when adding or testing tools, managing temporary files and image folders, configuring the working directory, or running the project's formatter and linter. The input does not describe the service's user-facing features in detail.
Why use it?
They give coding agents the local rules needed to change the project without placing server logic in the wrong module or using inconsistent formatting and checks.

Instructions file

not rated 0 1mo ago A scan 550 tokens original MIT
View the source file lka/recipe-tools
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/lka/recipe-tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/lka/recipe-tools

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 recipe-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lka/recipe-tools/claude-md.svg)](https://agentmods.dev/instructions/lka/recipe-tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lka/recipe-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/lka/recipe-tools/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 550 This file is loaded in full into every session.
When invoked 550 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 $0.00550 $0.00550
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 4d ago against content hash 28b86ff50310, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recipe-tools 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.

CLAUDE.md · 39 lines

What it actually says

CLAUDE.md

Projektstruktur, Installation und Befehle stehen in der README.md. Hier nur Architektur-Wissen und Konventionen fuer die Entwicklung.

Architektur-Pattern

  • Zentrale Server-Registrierung: server.py importiert reine Funktionen aus tools/ und wrapped sie mit @mcp.tool() + Logging. Tool-Module haben keine FastMCP-Abhaengigkeit.
  • FastMCP-Internals in Tests (FastMCP >= 3.0): asyncio.run(mcp.list_tools()) liefert Liste mit .name; asyncio.run(mcp.get_tool("name")) liefert Tool-Objekt mit .fn(); analog mcp.list_prompts() / mcp.get_prompt("name") fuer Prompts.
  • Shared Utils in core/: Gemeinsam genutzte Funktionen (get_working_dir, create_tmp_dir_if_needed, cleanup_tmp_dir, get_image_subdirectory) leben in core/utils.py. Image-selector-spezifisches (transform_coords) bleibt in image_selector/utils.py.
  • Working Directory: Wird ueber IMAGE_SELECTOR_WORKING_DIR Env-Var gesteuert (Fallback: os.getcwd()). Tests nutzen monkeypatch.setenv() mit tmp_path.

Code-Stil

  • Formatter: black (bestimmt Quote-Style → double quotes)
  • Linter: flake8 (Konfiguration in .flake8)
    • max-line-length = 88 (kompatibel mit black)
    • max-complexity = 10 (McCabe)
    • extend-ignore: E203, E501, W503, E402
    • Docstrings: Google-Style
  • Kein flake8-quotes – bewusst entfernt, black steuert Quotes
  • Sprache in Code/Docstrings: Deutsch (Umlaute in Docstrings vermieden, z.B. "ue" statt "ue")

Implementierungs-Details

  • Build-System: hatchling (build-backend = "hatchling.build")
  • Python >= 3.11 (verwendet str | None Union-Syntax)
  • gui.py-Methoden haben # pragma: no cover (Tkinter nicht testbar in CI)
  • _UNIT_PATTERN in html_builder.py: Case-sensitive (EL, TL sind Grossbuchstaben)
  • _clean_source Regex: (?<!/) Negative Lookbehind verhindert, dass Jahreszahlen nach "/" entfernt werden (z.B. "03/2025")
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. 4d ago First seen · 39 lines · 550 tokens per session scan A 28b86ff50310

Subscribe to this mod's changes

recipe-tools CLAUDE.md is an instructions file published in the GitHub repository lka/recipe-tools (0 stars, last pushed 1mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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.

beautifulsoupfastmcphtml-generatormcpmcp-serverocr
Related

Other instructions, from other repositories

ocr-mcp AGENTS.md

AGENTS.md instructions for sandraschi/ocr-mcp, covering ocr-mcp — agent guide, entry points, quick ref, standards and key files.

sandraschi/ocr-mcp · 299 tokens

ocr-mcp CLAUDE.md

Claude Code instructions for sandraschi/ocr-mcp, covering ocr-mcp — claude code guide, entry points, standards and key files.

sandraschi/ocr-mcp · 265 tokens

ocr-mcp copilot-instructions.md

Copilot instructions for sandraschi/ocr-mcp: You have access to a FastMCP 3.4+ OCR server with 14 backends for document text extraction.

sandraschi/ocr-mcp · 86 tokens

RivalSearchMCP AGENTS.md

AGENTS.md instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.

damionrashford/RivalSearchMCP · 2,638 tokens

mcp-outline CLAUDE.md

Instructions for Vortiago/mcp-outline, covering mcp outline server guide, purpose, architecture, tool categories and feature registration flow.

Vortiago/mcp-outline · 4,623 tokens

unraid CLAUDE.md

Claude Code instructions for dinglebear-ai/unraid, covering claude.md, what this is, identity and history (read before touching any url), "unraid-mcp" means five different things and agent plugins ship no claude code hooks.

dinglebear-ai/unraid · 3,561 tokens