Borrowing it
Nothing to install: this file belongs to marsmike/feinschmiede. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marsmike/feinschmiede/main/CLAUDE.mdgit clone --depth 1 https://github.com/marsmike/feinschmiedeWrote 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.
[](https://agentmods.dev/instructions/marsmike/feinschmiede/claude-md)<a href="https://agentmods.dev/instructions/marsmike/feinschmiede/claude-md"><img src="https://agentmods.dev/badge/instructions/marsmike/feinschmiede/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01752 | $0.01752 |
| Opus 5 | $0.00876 | $0.00876 |
| Sonnet 5 | $0.00350 | $0.00350 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
feinschmiede 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — feinschmiede repo
Working memory for AI contributors. Read before touching the master- template renderer, the diagram pipeline, brand packs, or the gallery publish flow.
North Star — shrink the suite, run it in half the time
Two goals every change pursues step by step:
- Decrease repository size and code complexity. Every non-trivial
PR should leave the suite smaller or simpler than it found it, or
have a concrete reason it cannot. Check
STATS.mdbefore and after — install footprint, source LOC, skill context cost. New features should subtract weight elsewhere; if the PR grows the install, call it out and offset it with a cut. Reject premature abstractions: three similar lines beats a generic helper. - Speed of execution. Default parallel-worker count for any
batch / CPU-bound script is
max(1, os.cpu_count() // 2), with a--workers Noverride flag. Half the cores keeps the operator's machine responsive. Wired into the gallery renderer; keep it consistent for any new batch-style code.
Master-template renderer
The deck pipeline is now ~500 LOC across six files under
feinschliff/feinschliff/master_template/ (ported from abzug). The
brand designer owns styling — master.pptx is the source of truth —
the renderer plays a list of FillPlan / ClonePlan entries against
it. No DSL, no picker, no compile step.
Public surface, called directly by skills and scripts:
from feinschliff import FillPlan, ClonePlan, render, apply_theme
The catalog inspector lives at feinschliff.master_template.catalog
and runs as python -m feinschliff.master_template.catalog <pack>.
Brand packs
Each pack lives at feinschliff/brands/<name>/ with three resolution
shapes for the master file:
master.pptx— the feinschliff convention.master/master.pptx— the abzug convention (BSH/Bosch v5).master.pptx.ref(text) — anhttp(s)://URL or a local path to the binary, kept outside the repo. URLs are fetched once into a gitignored.master.pptxcache beside the.ref. Used by the Microsoft-gallery packs (hosted on R2,assets.marsmike.com) and by private corporate packs (local asset directory).
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.
- 8d ago First seen · 151 lines · 1,752 tokens per session scan A a17ea3a15ae0
feinschmiede CLAUDE.md is an instructions file published in the GitHub repository marsmike/feinschmiede (3 stars, last pushed today), licensed MIT. It adds 1,752 tokens to every session, about $0.0088 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.
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.
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.
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).
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).
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.
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.