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 siberiacancode/agent-skills --skill juniors-best-practicegit clone --depth 1 https://github.com/siberiacancode/agent-skillsWrote 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/siberiacancode/agent-skills/juniors-best-practice)<a href="https://agentmods.dev/skills/siberiacancode/agent-skills/juniors-best-practice"><img src="https://agentmods.dev/badge/skills/siberiacancode/agent-skills/juniors-best-practice/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/siberiacancode/agent-skills/juniors-best-practice"><img src="https://agentmods.dev/badge/skills/siberiacancode/agent-skills/juniors-best-practice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00875 |
| Opus 5 | $0.00028 | $0.00438 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
juniors-best-practice 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 10d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Juniors Best Practice
Juniors-focused best practices for React and TypeScript projects. The rules are short, practical, and organized by scope to guide consistent code reviews, refactoring, and new feature work.
When to Apply
Reference these guidelines when:
- Writing or reviewing React/TypeScript code for clarity and consistency
- Teaching junior developers or establishing baseline team conventions
- Refactoring code to align with simple, maintainable patterns
- Standardizing project-wide practices (imports, tooling, naming, commits)
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Beginner Foundations | HIGH | beginner- |
| 2 | TypeScript | MEDIUM | typescript- |
| 3 | React | MEDIUM | react- |
| 4 | Styling | MEDIUM | styling- |
| 5 | Devtools | MEDIUM | devtools- |
| 6 | Assets | LOW-MEDIUM | assets- |
| 7 | Git | LOW | git- |
| 8 | REST | MEDIUM | rest- |
Quick Reference
1. Beginner Foundations (HIGH)
beginner-early-return- Prefer early returns to reduce nestingbeginner-double-negation- Avoid!isNotXpatternsbeginner-unnecessary-destructuring- Keep objects intact for claritybeginner-const-vs-let- Default to constbeginner-nullish-vs-or- Use ?? for defaultsbeginner-useless-return-arrow- Remove redundant returnbeginner-uppercase-constants- Use UPPER_CASE only for stable constants
2. TypeScript (MEDIUM)
typescript-alias-naming- Use safe path alias prefixestypescript-flat-translations- Prefer flat translation keys to reduce duplication
3. React (MEDIUM)
react-string-props- Use string literals when possiblereact-children-prop- Use children for compositionreact-extends-component- Extend native element propsreact-props-typing- Keep props typing readable
What ships with it
27 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.
- AGENTS.md 4.0 KB
- metadata.json 484 B
- README.md 2.3 KB
- rules/_sections.md 1.3 KB
- rules/_template.md 564 B
- rules/assets-svg-files.md 1.7 KB
- rules/beginner-const-vs-let.md 501 B
- rules/beginner-double-negation.md 660 B
- rules/beginner-early-return.md 888 B
- rules/beginner-nullish-vs-or.md 936 B
- rules/beginner-unnecessary-destructuring.md 903 B
- rules/beginner-uppercase-constants.md 829 B
- rules/beginner-useless-return-arrow.md 588 B
- rules/devtools-formatter-linter.md 598 B
- rules/devtools-package-manager-lock.md 635 B
- rules/devtools-sorting-imports.md 950 B
- rules/git-commit-convention.md 907 B
- rules/react-children-prop.md 795 B
- rules/react-extends-component.md 908 B
- rules/react-props-typing.md 485 B
- rules/react-string-props.md 505 B
- rules/rest-naming-openapi.md 988 B
- rules/rest-scalability-abstractions.md 1.1 KB
- rules/styling-classnames-function.md 1.4 KB
- rules/styling-css-states.md 1.1 KB
- rules/typescript-alias-naming.md 743 B
- rules/typescript-flat-translations.md 750 B
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.
- 10d ago First seen · 103 lines · 55 tokens per session scan A c61a2e9f6a61
juniors-best-practice is a skill published in the GitHub repository siberiacancode/agent-skills (19 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 875 once invoked, about $0.0003 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
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
nextjs-app-router
Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
react-query-setup
Set up @trpc/tanstack-react-query with createTRPCContext(), TRPCProvider, useTRPC() hook, queryOptions/mutationOptions factories, query invalidation via queryClient.invalidateQueries with queryFilter, and type inference with inferInput/inferOutput.
react-query-classic-migration
Migrate from @trpc/react-query (classic) to @trpc/tanstack-react-query. Run npx @trpc/upgrade CLI for automated codemod. Manually migrate remaining patterns: hook-based to options-factory, utils.invalidate to queryClient.invalidateQueries with queryFilter, provider changes.
image-to-threejs
REQUIRES uv + Python 3.12 and a one-time git clone — unlike the other asset skills, this one is not Node-only. Turn a generated reference image into a rigged, procedural Three.js prop — code, not a mesh file. Generate ONE clean product-shot reference with vg generate, author a component spec (parts, materials, pivots…