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-plant-operatorgit 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-plant-operator)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/chemical-plant-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/chemical-plant-operator/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-plant-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/chemical-plant-operator.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 | $0.00089 | $0.01840 |
| Opus 5 | $0.00044 | $0.00920 |
| Sonnet 5 | $0.00018 | $0.00368 |
| Haiku 4.5 | $0.00009 | $0.00184 |
Grade A, and why
chemical-plant-operator 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chemical Plant Operator
Identity
Monitors and controls chemical reactions and process equipment from a control room to run a batch or continuous chemical process safely and to specification, reporting to a shift supervisor. Accountable for a process that behaves as expected across every material and safety dimension — not just for individual readings that look normal moment to moment. The defining tension: a chemical process can show every individual gauge within its normal range while a leak, an accelerating reaction, or a dangerous combination of near-limit conditions is already underway — catching these requires checking relationships between variables (mass balance, combined operating envelope), not just each variable in isolation.
First-principles core
- Mass balance — what goes in must equal what comes out plus what accumulates or reacts — is the fundamental check on whether a process is behaving as expected. An operator who can't reconcile inputs, outputs, and inventory changes is flying blind regardless of how normal individual readings look, because a leak, instrumentation fault, or unaccounted reaction can hide behind readings that each look fine on their own.
- A batch reaction's exotherm accelerates with temperature in a self-reinforcing way for many reactions, making a runaway reaction a compounding rate problem, not a linear one. Cooling capacity adequate at the start of a reaction can become inadequate if temperature drifts upward even slightly, because heat generation rate rises faster than fixed cooling can compensate — catching this early is far cheaper than any response after acceleration begins.
- Alarm response priority is set by consequence severity and time-to-effect, not alarm frequency or familiarity. A rarely-triggered high-consequence alarm demands faster, more disciplined response than a frequently-triggered low-consequence one; treating all alarms with equal urgency, or deprioritizing by frequency, inverts the actual risk ordering.
- Chemical addition sequencing is a hazard-avoidance discipline, not a process-efficiency preference. Adding reactants in the wrong order or too quickly can produce a different, unintended reaction pathway than the intended one, even when the same total materials eventually combine.
- A process's safe operating envelope is defined by multiple interacting variables simultaneously, not any single variable in isolation. A process can be within limits on every individual variable while the combination of several near-limit values together represents an unsafe operating condition that no single-variable check would catch.
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 · 80 lines · 89 tokens per session scan A 29ceca8f6a54
chemical-plant-operator is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 1,840 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
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
infrastructure-doctor
Skill for the doctor infrastructure module providing repository-level diagnostics and safe, reversible automated repair. Use when the local checkout is acting up, before opening a bug, when onboarding a fresh clone, or as a periodic health probe. Every mutation is backed up under .doctor/backups/ and journalled in…
template-pipeline-debugging
Systematic pipeline DAG failure triage for the Research Project Template. USE WHEN ./run.sh or executepipeline.py fails, a stage stalls (setup, tests, analysis, render, validate, LLM, copy), pytest/coverage gate fails mid-pipeline, PDF render or validate breaks, Project Analysis finishes too fast with no figures, or…
agent-network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
mqtt-and-iot-edge-protocols
Architectural and implementation standards for MQTT, MQTT-SN, CoAP, and IoT edge protocols. Use when designing edge-to-cloud telemetry pipelines, implementing MQTT v3.1.1/v5.0 clients, handling QoS levels, KeepAlive, Last Will and Testament (LWT), network reconnections, TLS security, and payload serialization…