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.
npx agentmods add skills/marsmike/feinschmiede/decknpx skills add marsmike/feinschmiede --skill deckgit 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/skills/marsmike/feinschmiede/deck)<a href="https://agentmods.dev/skills/marsmike/feinschmiede/deck"><img src="https://agentmods.dev/badge/skills/marsmike/feinschmiede/deck.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 | $0.00027 | $0.00778 |
| Opus 5 | $0.00014 | $0.00389 |
| Sonnet 5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
deck scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deck — master-template renderer
Generate a brand-perfect .pptx by composing plans against a brand pack's master.pptx. The master supplies typography, colors, footers, slide-number chrome — the renderer only fills placeholders and clones bespoke shapes.
Quick Start
from pathlib import Path
from feinschliff import FillPlan, render
render(
Path("feinschliff/brands/feinschliff"),
[FillPlan(layout="Title Slide", fills={0: "Q3 update", 1: "Roadmap"})],
Path("out.pptx"),
)
Author the call in feinschliff/.debug/<topic>-<date>/build.py and run it with feinschliff build.py — the plugin's launcher execs the venv Python directly, no CLI in between.
Brand packs
Each pack ships under feinschliff/brands/<name>/ with a master.pptx (or .ref pointer) and catalog files. Built-in packs: feinschliff (default), annual-review, geometric, scientific, shapes, gs-ramspau. Corporate / private packs surface through sibling feinschliff-* plugin directories ($FEINSCHLIFF_BRAND_PATH). Run python -m feinschliff.master_template.catalog <brand_pack> to list layouts + snippets for any pack.
Mental model
A deck is a list of plans, in slide order:
FillPlan(layout, fills)— pick a layout by name (see<brand>/layouts.yaml), fill placeholders byidx. Values:str,list[str],PictureRef, orChartSpec. Charts and pictures replace the OBJECT placeholder.ClonePlan(source_idx, replacements)— XML-clone a bespoke source slide from<brand>/snippets.yaml.replacementsis a queue per old-string; repeating("Milestone", ...)consumes successive occurrences in document order.render(..., theme=Path|dict)— optional. Patches the master'stheme1.xml<a:clrScheme>from a small JSON. Onemaster.pptx, N visual variations; the file on disk is never touched.
Flow
- Interview if the brief is thin. Topic + audience are the minimum; references/storyline.md maps audience to a default slide count.
- Draft the storyline per references/storyline.md — emit the brief block + numbered slides block, pick a frame, tag each row with
roleandact, write claim-style titles. - Pick layouts per references/layouts.md. For bespoke shapes (timelines, funnels, infographics) clone from
<brand>/snippets.yaml— see references/clones.md for the text-anchor recipe. - Approval gate — show storyline + chosen layouts, ask "ok?". Don't render until approved.
- Render with the Quick Start snippet. Respect the verbosity tier when sizing fills. See references/gotchas.md for pitfalls.
- Verify and loop — convert to PDF and read the pages against the defect classes in references/verify.md. Fix and re-render until clean; the reference describes the
/loop-driven iteration.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 45 lines · 27 tokens per session scan A 55ef0045de21
deck is a skill published in the GitHub repository marsmike/feinschmiede (3 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 778 once invoked, about $0.0001 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 skills, from other repositories
iso-13485-certification
Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work…
pptx-posters
Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual…
report-generator
高级报告生成专家，支持多格式输出、数据可视化和交互式报告生成。.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
scholarly-publishing
Use when planning an end-to-end scholarly publishing workflow, including manuscript source-of-truth, submission assets, revision/rebuttal files, camera-ready checks, reproducible build expectations, and publication package structure.