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 skills add ScottDuncanAI/claude-manufacturing-skills --skill pfd-generatorgit clone --depth 1 https://github.com/ScottDuncanAI/claude-manufacturing-skillsWrote 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/scottduncanai/claude-manufacturing-skills/pfd-generator)<a href="https://agentmods.dev/skills/scottduncanai/claude-manufacturing-skills/pfd-generator"><img src="https://agentmods.dev/badge/skills/scottduncanai/claude-manufacturing-skills/pfd-generator/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.
<a href="https://agentmods.dev/skills/scottduncanai/claude-manufacturing-skills/pfd-generator"><img src="https://agentmods.dev/badge/skills/scottduncanai/claude-manufacturing-skills/pfd-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 12 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00106 | $0.02735 |
| Opus 5 | $0.00053 | $0.01367 |
| Sonnet 5 | $0.00021 | $0.00547 |
| Haiku 4.5 | $0.00011 | $0.00274 |
Grade A, and why
pfd-generator 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 12d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PFD Generator
Produce a conceptual PFD as a hand-authored SVG that a process engineer would accept: correct process flow, correct ISA instrumentation, closed control loops, and a layout with zero collisions and zero crossed process lines.
The output is judged by an engineer who will spot a backwards arrowhead, a steam coil above the liquid level, or a label sitting under a balloon. Accuracy and legibility rank above speed.
Non-negotiable output rules
- No hidden text. Every label must be fully readable. Nothing may sit under a line, balloon, valve, vessel, or another label.
- No crossing process lines. Solve crossings by re-planning elevations, not by drawing over. If one is truly unavoidable, draw a proper line jump (semicircular hop).
- Control loops must be complete and directional. Every loop is measurement → controller → final element, with an arrowhead on each leg. A signal line without an arrowhead is a defect.
- Text is real
<text>, never glyph paths or outlines. The user must be able to edit labels in a text editor. Never emit a matplotlib/Illustrator-style SVG where letters are<use>or<path>references. - Minimum font size 8.5. Tag text 10–11.5, line labels 11–13, title 20–22. Nothing smaller than 8.5 survives a slide deck.
- Elevations must be physically true. See Rule of elevation below.
Workflow
1. Read the description and fill the gaps
A process description almost always underspecifies the drawing. Before drawing, resolve:
- What is the controlled variable, and what is the final control element?
- Are any loops cascaded? Which is master, which is slave?
- Where does each stream enter and leave the vessel (top, bottom, side; above or below liquid level)?
- What is the heating/cooling medium and its return path?
- Any redundant or voting instruments?
Ask at most 2–3 questions, and only for things that change the drawing. For anything minor, make a defensible engineering assumption and state it in the response afterward. Do not stall the drawing over detail that can be noted as an assumption.
What ships with it
7 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.
- 12d ago First seen · 164 lines · 106 tokens per session scan A c25b783a2b08
pfd-generator is a skill published in the GitHub repository ScottDuncanAI/claude-manufacturing-skills (51 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 2,735 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.