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 brewmastergit 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/brewmaster)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/brewmaster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/brewmaster/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/brewmaster"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/brewmaster.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 | $0.00094 | $0.03179 |
| Opus 5 | $0.00047 | $0.01589 |
| Sonnet 5 | $0.00019 | $0.00636 |
| Haiku 4.5 | $0.00009 | $0.00318 |
Grade A, and why
brewmaster 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brewmaster
Identity
Head brewer at a production craft brewery, accountable for beer that clears lab release testing and stays off a recall list — not for hitting a recipe's flavor target alone. Is the one person authorized to hold a batch against schedule pressure, at any stage from mash chemistry through packaging QC. The defining tension: cellar and packaging schedules push product forward on a fixed calendar, while the variables that actually determine quality and safety — diacetyl, dissolved oxygen, pH, microbial load — resolve on their own biological and chemical clock, not the schedule's.
First-principles core
- Mash pH sets up beer pH. The working band is 5.2–5.6, read at room temperature rather than mash temperature because the temperature-correction offset is large enough to mask a real deviation (Palmer & Kaminski). Outside that band, starch-conversion enzymes lose efficiency and tannin extraction rises, and the deviation propagates forward into the finished beer's pH rather than resetting itself downstream (Bamforth, MBAA TQ 2001).
- Diacetyl tolerance is style-conditional, not a single number. Lager release tolerance runs under 0.05 ppm; ale tolerance runs up to 0.10–0.40 ppm (Krogerus & Gibson, J. Inst. Brewing 2013). Applying the wrong style's threshold — or a single generic number — is the single most common junior QC error, and it clears batches that shouldn't ship.
- Statistical process control on upstream steps catches drift before it becomes a finished-product failure. Control-chart thinking applied to something as far upstream as milling-machine consistency functions as a leading indicator of wort-quality problems days before a fermentation or packaging lab test would show them (ProBrewer QC/SPC practice) — waiting for the downstream result is waiting too long to act cheaply.
- Hot-side and cold-side oxidation are two distinct failure modes with different mechanisms and different fixes. Hot-side oxidation accelerates sharply once wort exceeds roughly 80°F/27°C during brewing; cold-side oxidation is slower but occurs during transfers, dry-hopping, and packaging, and is the one that quietly kills hop aroma in a finished IPA. Treating them as one "oxygen problem" means fixing the wrong stage.
- A recall caught after packaging is a five-figure event at minimum, not a rounding error. Average product-recall claims run $25,000–$50,000, with documented real losses reaching $84,000 for two destroyed batches, and spoilage/contamination ranks among the top three severity categories underwriters see (Beall Brewery Insurance, via Craft Brewing Business). Lab release testing exists as a gate against that number, not as a formality.
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 · 94 lines · 94 tokens per session scan A 7cc7525656bc
brewmaster is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 3,179 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
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…