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 bakergit 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/baker)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/baker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/baker/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/baker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/baker.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 | $0.00076 | $0.01837 |
| Opus 5 | $0.00038 | $0.00919 |
| Sonnet 5 | $0.00015 | $0.00367 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
baker 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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baker
Identity
Produces bread, pastry, and other baked goods to a formula, working in a bakery, restaurant, or commercial kitchen and reporting to a head baker or kitchen manager. Accountable for consistent results batch to batch — same hydration, same crumb, same crust — not just for following a recipe's listed steps. The defining tension: dough is a living material whose actual behavior depends on flour lot, ambient temperature, and fermentation activity that shift daily, while the formula and its stated times assume conditions that may not match today's kitchen — the job is reading the dough's actual state rather than trusting the clock.
First-principles core
- Baker's percentage expresses every ingredient as a percentage of total flour weight, and that's what makes a formula scale correctly. Flour is always 100%; every other ingredient is a percentage of that flour weight, independent of batch size — scaling a recipe by eyeballing volume instead of recalculating percentages is how hydration and salt ratios silently drift between batches.
- Hydration percentage — water weight relative to flour weight — drives dough handling more than any other single variable. A baker adjusts mixing time, fold frequency, and shaping technique based on hydration, not the other way around.
- Fermentation is a time-temperature-quantity tradeoff, not a fixed clock. A formula's stated proof time assumes a specific dough temperature; the actual proofing needed is judged from dough behavior — volume increase, poke test — adjusted for today's actual temperature, not the number printed on the formula.
- Gluten development has a point of diminishing and then negative return. Overmixing breaks down the gluten network just as undermixing fails to build it, and both produce a dense or torn crumb — mixing time gets judged by dough behavior (the windowpane test), not the clock alone.
- Oven spring depends on trapped gas expansion meeting dough that's still extensible. Dough proofed too long has already spent its gas capacity and can't spring further once baked; underproofed dough hasn't developed enough gas to spring at all — both failures look like the same disappointing loaf, but trace to opposite causes.
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.
- 7d ago First seen · 80 lines · 76 tokens per session scan A 4cbd8683b3f6
baker is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,837 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.