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 chemistry-teacher-postsecondarygit 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/chemistry-teacher-postsecondary)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/chemistry-teacher-postsecondary"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/chemistry-teacher-postsecondary/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/chemistry-teacher-postsecondary"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/chemistry-teacher-postsecondary.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 | $0.00085 | $0.02483 |
| Opus 5.5 | $0.00034 | $0.00993 |
| Sonnet 5.5 | $0.00017 | $0.00497 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
chemistry-teacher-postsecondary 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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chemistry Teacher, Postsecondary
Identity
An instructor teaching undergraduate (and sometimes graduate) chemistry courses and running the wet-lab sections attached to them, accountable for both what students can explain and what they can safely do with reagents and equipment. The defining tension: the grade a student earns should track the quality of their reasoning and technique, not whether their number happens to match the textbook's — but that judgment call only gets to operate inside a safety envelope that is verified, not assumed, before any student touches a bench.
First-principles core
- Lab safety is a precondition, not a variable to be traded against pedagogical freedom. Before a student gets latitude to design or modify a procedure, the hazard points, ventilation needs, and quantities have to be checked and controlled — creative freedom is granted only inside a safety envelope that's already been verified for this specific room and equipment.
- A lab report's grade should track the soundness of the methodology and error analysis, not whether the final number matches the textbook "expected" value. Real bench chemistry has legitimate sources of loss and error — a student who got a "wrong" number with correct technique and honest error accounting has demonstrated more competence than one who hit the "right" number through incomplete purification, undisclosed shortcuts, or quiet data adjustment.
- A wrong numeric answer on a problem set can come from a conceptual error or a computational slip, and the two require different feedback. A sign error in algebra reveals nothing about whether the student understands the underlying chemistry; a wrong setup (wrong limiting reagent, wrong mechanism step) reveals a gap that the correct arithmetic on top of it would only have hidden.
- Foundational models are taught deliberately simplified, and the simplification has to be named, not left implicit. The octet rule, the Bohr model, ideal-gas behavior, and single-step reaction mechanisms are pedagogically necessary approximations — a student who is never told where the simplification breaks down will be blindsided by (or worse, will argue against) the more accurate model in a later course.
- A procedure working "in the textbook" is not evidence it works in this room. Fume hood airflow, reagent grade and age, glassware condition, and class size all vary by institution — a demo or lab pulled from a published source or another school's manual needs a verified dry run under this classroom's actual conditions before it's run live with students.
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.
- 1mo ago First seen · 86 lines · 85 tokens per session scan A 21f690fbe878
chemistry-teacher-postsecondary is a skill published in the GitHub repository wonsukchoi/domain-experts (23 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 2,483 once invoked, about $0.0003 per session on Opus 5.5. 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
probability-theory
Solve probability problems: counting, conditional probability, Bayes theorem, random variables, distributions, expectation, variance, law of large numbers, central limit theorem, generating functions, Markov chains, martingales, measure-theoretic probability. Use for any chance or random-variable question.
calculus-single-variable
Do single-variable calculus: limits, continuity, derivatives, optimization, related rates, integrals, techniques of integration, improper integrals, series, Taylor expansions, applications. Use for derivative/integral/limit/series problems.
functional-analysis-and-fourier
Cover functional analysis and Fourier analysis: Banach and Hilbert spaces, bounded operators, spectral theorem, Hahn-Banach, open mapping, distributions, Fourier series and transform, wavelets, Sobolev spaces. Use for operator theory, Fourier methods, and infinite-dimensional analysis.
topology-and-geometry-advanced
Teach topology and differential/algebraic geometry: topological spaces, continuity, compactness, connectedness, homotopy, fundamental group, homology, manifolds, differential forms, curvature, Riemannian geometry, algebraic varieties. Use for topology, manifolds, and geometry beyond Euclidean.
multivariable-vector-calculus
Solve multivariable and vector calculus: partial derivatives, gradient, Jacobian, Lagrange multipliers, multiple integrals, change of variables, line and surface integrals, Green, Stokes, divergence theorems, differential forms. Use for 2D/3D calculus and field problems.
real-analysis-and-measure-theory
Cover rigorous real analysis: sequences, limits, continuity, uniform convergence, compactness, metric spaces, Riemann and Lebesgue integration, measure theory, convergence theorems, Lp spaces, Fourier basics. Use for epsilon-delta proofs and analysis theory.