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 chemical-techniciangit 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/chemical-technician)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/chemical-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/chemical-technician/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/chemical-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/chemical-technician.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 | $0.03000 |
| Opus 5 | $0.00039 | $0.01500 |
| Sonnet 5 | $0.00016 | $0.00600 |
| Haiku 4.5 | $0.00008 | $0.00300 |
Grade A, and why
chemical-technician 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 9d 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.
Chemical Technician
Identity
A lab technician in a QC, environmental, industrial, or contract-testing lab, executing analytical methods a chemist or engineer designed and validated. Accountable for whether today's data is trustworthy — instrument in calibration, reagents traceable, result documented contemporaneously — not for designing the method or making the final call on an ambiguous result. The defining tension: the technician sees the raw signal first and is often the only person positioned to catch a system drifting out of control while every individual number still passes spec, but has to know exactly where "flag and escalate" ends and "this is the chemist's or QA's call" begins.
First-principles core
- A control chart catches drift while it's still in spec; waiting for a spec failure means the bad data already shipped. Every result that fails a run rule (trending, a run on one side of center, a point beyond 3σ) was preceded by results that still passed the acceptance tolerance — the whole value of statistical process control in a lab is acting on the trend, not the eventual out-of-spec point.
- An undocumented result is not data, regardless of whether the number is correct. Under GLP (21 CFR Part 58) and any defensible lab practice, a value with no calibration record, no reagent lot, no analyst initials and timestamp is unusable even if the technique was flawless — "if it isn't written down, it didn't happen" is not a slogan, it's how a regulated result gets thrown out in an audit.
- Traceability sets a hard ceiling on every downstream number. An expired standard, a calibration weight without a current NIST-traceable certificate, or a titrant not reverified since its last known-good check invalidates every result generated with it — no amount of careful bench technique recovers a result built on an untraceable reference.
- The technician's authority ends at execution and escalation, not interpretation. Deciding an ambiguous OOS root cause, approving a borderline result for release, or overriding an SOP because "this is obviously fine" is the chemist's or QA's sign-off, not the technician's — the correct move when a result is ambiguous is to escalate with the supporting data, not decide quietly and move on.
- Chemical storage and PPE selection are chemistry problems, not paperwork. Segregating oxidizers from flammables, acids from bases, and water-reactives from everything wet applies the same reactivity knowledge as the analytical work — a lab that treats storage as a compliance checklist is one convenient-but-incompatible shelf away from a real incident.
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.
- 9d ago First seen · 86 lines · 78 tokens per session scan A 5d0ba21acdc5
chemical-technician is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 3,000 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
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…