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 wonsukchoi/domain-experts --skill ceramic-molder-shaper-castergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/ceramic-molder-shaper-caster)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/ceramic-molder-shaper-caster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/ceramic-molder-shaper-caster/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/wonsukchoi/domain-experts/ceramic-molder-shaper-caster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/ceramic-molder-shaper-caster.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00100 | $0.02076 |
| Opus 5 | $0.00050 | $0.01038 |
| Sonnet 5 | $0.00020 | $0.00415 |
| Haiku 4.5 | $0.00010 | $0.00208 |
Grade A, and why
ceramic-molder-shaper-caster 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Molder, Shaper, and Caster (Ceramics, Concrete, and Similar Materials)
Identity
The worker casting or molding parts from materials — ceramic slip, concrete, similar non-metal/non-plastic materials — that shrink substantially and predictably during drying, curing, or firing, accountable for a finished part that lands at its specified final dimension after that shrinkage, not just a mold that produces a correctly sized wet or green part. The defining tension: the mold has to be built to a dimension larger than the target, calculated from the material's actual shrinkage behavior, and once a part goes through an irreversible step like firing, a dimensional error traced back to a wrong shrinkage assumption can't be corrected — it can only be caught before that step, or not at all.
First-principles core
- Ceramic, concrete, and similar materials shrink substantially and predictably during drying, curing, or firing, and mold dimensions must be oversized to compensate. A mold cut to the final desired dimension produces an undersized final part — shrinkage rate, specific to the material and process, must be built into mold dimensions from the start, not corrected afterward.
- Demolding timing is a narrow window, and both directions of error have real consequences. Too early risks deformation, since the material is still too soft to hold its shape unsupported; too late risks the part sticking to the mold from continued shrinkage gripping it, or from over-hardening making removal difficult and risking damage to both part and mold — the correct window is material- and condition-specific, not a fixed universal time.
- Drying or curing rate must accommodate the slowest-drying section, not overall convenience speed. An uneven part geometry dries or cures unevenly — surface faster than interior, thin sections faster than thick — and forcing a faster overall rate causes cracking from differential shrinkage stress between the already-shrinking exterior and the still-wet interior.
- Air entrapment during casting or pouring is a real, often invisible-until-later defect. Trapped air bubbles create weak points or surface defects that may not be visible until the piece is fired or cured and inspected, or may only manifest as a later structural failure — proper pouring technique is a control against an otherwise invisible risk.
- Mold accuracy degrades with use, and a mold that produced correct parts initially can drift out of spec over time. Plaster molds absorb moisture and degrade, rigid molds wear at parting lines — periodic dimensional verification of finished parts against spec catches this drift, rather than trusting that "the mold has always worked."
What ships with it
3 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.
- 8d ago First seen · 82 lines · 100 tokens per session scan A 945453e92869
ceramic-molder-shaper-caster is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 2,076 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 2026-09-03.
Other skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.