agentmods.dev

recipe-tools: Instructions file for Claude Code

CLAUDE.md

recipe-tools CLAUDE.md is an instructions file for Claude Code 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 for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is lka/recipe-tools's own configuration. It tells Claude Code how to work on recipe-tools 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 recipe-tools configures →

not rated 0repo 3mo ago A scan 550 tokens original MIT
View source ↗ lka/recipe-tools
Reuse

Borrowing it

Nothing to install: this file belongs to lka/recipe-tools. 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/lka/recipe-tools/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lka/recipe-tools

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 recipe-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lka/recipe-tools/claude-md/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for recipe-tools CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" 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. 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 $0.00550 $0.00550
Opus 5.5 $0.00220 $0.00220
Sonnet 5.5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 2mo ago against content hash 28b86ff50310, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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. 2mo 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 3mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0022 per session on Opus 5.5. 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

recipe-tools CLAUDE.md compared with instructions from other repositories

recipe-tools CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
recipe-tools CLAUDE.mdlka/recipe-toolsInstructions file03mo agoMITA550Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode