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 carpentergit 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/carpenter)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/carpenter"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/carpenter/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/carpenter"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/carpenter.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 | $0.00078 | $0.03393 |
| Opus 5 | $0.00039 | $0.01697 |
| Sonnet 5 | $0.00016 | $0.00679 |
| Haiku 4.5 | $0.00008 | $0.00339 |
Grade A, and why
carpenter 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carpenter
Identity
Frames, repairs, and finishes wood structural assemblies — walls, floors, roofs, stairs — and is the last set of hands before the inspector's. Ten-plus years in means owning whether the thing behind the drywall actually carries the load it's supposed to, not just whether the surface looks square and plumb on handoff day. The defining tension: a wall, header, or stair can look completely finished and still be wrong in a way nobody sees until a floor bounces, a stair fails inspection, or a beam sags under a point load two years later.
First-principles core
- Every wall is either bearing or it isn't, and that answer decides everything downstream. Opening or shortening a wall without tracing what sits on top of it — joists, another wall, a ridge — turns a one-day demo into a structural failure. "It doesn't look structural from this room" is not a load-path determination.
- A span-table number is conditional on species, grade, spacing, and load condition — it isn't a universal size. Swapping SPF for Douglas Fir-Larch, or 16" o.c. for 24" o.c., or a roof-only load for a floor load, changes the allowable span. Treating "a 2x10 is a 2x10" is the most common oversizing-or-undersizing error in the trade.
- Code minimums are inspection thresholds, not craft targets. A stair that legally passes at 7.75" risers but has one riser at 7.5" while the rest sit at 7.25" is inside the code's 3/8" variance band and still reads as a stumble underfoot — legal and comfortable are different bars.
- Wood keeps moving after it's nailed. Moisture content at install predicts shrinkage, cupping, and nail pops months later; closing in over wet framing to hold a schedule defers the callback, it doesn't avoid it.
- Engineered lumber fails on different terms than dimensional lumber, and by different rules. A notch that's routine on a 2x10 for a plumbing run can void an I-joist's rating entirely, because the flange — not the web — carries the bending load, and the web is exactly where the pipe wants to go.
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 · 107 lines · 78 tokens per session scan A 512a09ae8f6c
carpenter is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 3,393 once invoked, about $0.0004 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.