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 HoangNguyen0403/agent-skills-standard --skill common-operator-profilegit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/common-operator-profile)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/common-operator-profile"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-operator-profile/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/hoangnguyen0403/agent-skills-standard/common-operator-profile"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/common-operator-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00079 | $0.00925 |
| Opus 5 | $0.00039 | $0.00463 |
| Sonnet 5 | $0.00016 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
common-operator-profile 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 13d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operator Profile
Priority: P0 (CRITICAL)
1. Infer, Never Ask
Classify the requesting operator into exactly one tier from message content alone. Do not ask "how technical are you?" or similar — inference only. Treat the tier as internal response context: continue with the requested work in that register. Never return only business, hybrid, or technical as the answer.
| Tier | Signal |
|---|---|
technical |
Names files, branches, PRs, diffs, frameworks, stack traces, ticket IDs, or existing code. |
hybrid |
Fluent in one stack, asks definitional questions about another ("I know Laravel, new to NestJS"). |
business |
Outcome/goal language only, no code or file artifacts, business vocabulary ("customers", "revenue", "an app that tracks..."). |
Default to hybrid when ambiguous. Revise silently as new evidence arrives in the same session; never re-ask. The profile is decided once per session and carried forward as operator_profile in every Handoff Payload so downstream workflows never re-infer it.
An explicit profile=business|hybrid|technical invocation argument always overrides inference.
For traceable workflow output, name the inferred register once when it matters (for example, Profile: business or Profile: technical) and then continue with the substantive answer. Never return only the label. File paths, requirement IDs, and test references such as prd-checkout.md and checkout.spec.ts are technical signals even when the request is otherwise brief.
2. Register Rules Per Tier
business: Lead every response with a plain-language outcome summary (what changes for the business, no jargon). Move file paths, IDs, commands, and stack detail into a trailing "Technical Appendix" the operator can skip. Frame Blocking Questions as business choices, each with a recommended default answerable by "go with your suggestion." Proxy purely technical decisions (tech stack internals, library choice) without asking — record them as assumptions, not blockers.hybrid: Full technical detail. Define unfamiliar-stack concepts on first use and map them to the operator's declared home stack when known (e.g., map a NestJSModuleorProviderto its Laravel equivalent).technical: Terse, full detail, no explanations of standard concepts. If essential artifacts are unavailable, name the exact supplied requirement, file, or test needed; do not replace the task response with a profile label.
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.
- 13d ago First seen · 60 lines · 79 tokens per session scan A 2eed435027b0
common-operator-profile is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 925 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 2026-08-30.
Other skills, from other repositories
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
oma-frontend
Frontend specialist for React, Next.js, Angular, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS work.
design-patterns
Frontend design patterns with React 19.2 and TypeScript 6 examples (Composition, Compound Components, Custom Hooks, Render Props, HOC, State Machines). Use when user asks "implement pattern", "use composition", or when designing reusable components.
react-nextjs
React 19.2 + Next.js 16 development - Server Components, Cache Components, proxy.ts, View Transitions, App Router, TypeScript 6, and Tailwind CSS v4. Use when building frontend apps, creating components, or asking "how do I set up X?".
code-quality
Comprehensive frontend code review for TypeScript 6 and React 19.2 — clean code principles, component patterns, type safety, accessibility, and performance. Use when user says "review code", "refactor", "check this PR", or before merging changes.
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.