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 aiko-atami/effectorjs-skills --skill argon-routergit clone --depth 1 https://github.com/aiko-atami/effectorjs-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/aiko-atami/effectorjs-skills/argon-router)<a href="https://agentmods.dev/skills/aiko-atami/effectorjs-skills/argon-router"><img src="https://agentmods.dev/badge/skills/aiko-atami/effectorjs-skills/argon-router/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/aiko-atami/effectorjs-skills/argon-router"><img src="https://agentmods.dev/badge/skills/aiko-atami/effectorjs-skills/argon-router.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 | $0.00076 | $0.01013 |
| Opus 5 | $0.00038 | $0.00507 |
| Sonnet 5 | $0.00015 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
argon-router 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argon Router
Use this skill to implement argon-router in React web apps with predictable Effector dataflow and typed paths.
Workflow
- Classify the task:
setup: create route map, router, and controls.ui: connect router to React views, links, and outlet.native: integrate argon-router with React Navigation in React Native.query: track URL query state and sync enter/exit flows.composition: build derived/protected/virtual routes.adapters: pick and configure history/query/custom adapter.ssr: scope-safe initialization with memory history andallSettled.hooks: route activity and router access hooks in React.debug: validate path/router wiring and route lifecycle.
- Load only required references:
- Always start with
references/core-routing.md. - Add
references/react-web.mdfor any React integration task. - Add
references/react-native.mdfor React Native stack/tabs integration. - Add
references/paths-dsl.mdwhen working with route path syntax or parsing/building URLs. - Add
references/query-tracking.mdwhen query params or filters are involved. - Add
references/route-composition.mdwhen using auth guards, grouped states, or virtual routes. - Add
references/adapters-ssr.mdforhistoryAdapter/queryAdapter, adapter selection, SSR bootstrap. - Add
references/react-navigation-apis.mdforLink,useRouter,useRouterContext,useIsOpened,useOpenedViews. - Add
references/lazy-layout.mdforcreateLazyRouteViewandwithLayout. - Add
references/examples.mdfor copyable happy-path scaffolds. - End with
references/checklist.mdbefore final output.
- Resolve source of truth before implementation:
- Prefer
../argon-router/packages/*/lib/*.tsand packagelib/index.tsexports. - Use docs as explanatory context and examples.
- If docs and code differ, follow code behavior and note mismatch briefly.
- Build in this order:
- Define route units with explicit paths and params.
- Create router controls and initialize history adapter.
- Create router with known routes, optional base, and explicit pathless mapping (
{ path, route }) when needed. - Create React route views and wire
RouterProvider+createRoutesView(addotherwisewhen fallback behavior is required). - Add link/navigation actions via route
openandLinkfirst. - Use
useLinkonly for custom interaction surfaces. - Add dynamic registration (
router.registerRoute(...)) only if runtime extension is required. - Add query trackers only when URL query behavior is required.
- Add route composition (
chainRoute,group) after baseline routing works. - Add lazy/layout organization (
createLazyRouteView,withLayout) when route tree is stable.
What ships with it
12 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/openai.yaml 284 B
- references/adapters-ssr.md 1.6 KB
- references/checklist.md 2.5 KB
- references/core-routing.md 2.4 KB
- references/examples.md 1.7 KB
- references/lazy-layout.md 1.3 KB
- references/paths-dsl.md 917 B
- references/query-tracking.md 1.3 KB
- references/react-native.md 1.6 KB
- references/react-navigation-apis.md 1.6 KB
- references/react-web.md 2.0 KB
- references/route-composition.md 1.3 KB
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 · 80 lines · 76 tokens per session scan A 22015495bd34
argon-router is a skill published in the GitHub repository aiko-atami/effectorjs-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 76 tokens to every session and 1,013 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 2026-08-31.
Other skills, from other repositories
frontend-conventions
Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.
improve-threejs
Audit and fix Three.js and React Three Fiber apps for frame-loop performance, GPU memory leaks, scene-graph correctness, and visual defects like z-fighting, shadow acne, wrong color space, and broken resize handling. Uses React Doctor as the scanning engine plus a visual rubric checked against rendered output. Use…
performance
Diagnose React runtime performance with React Doctor traces, live render outlines, Long Animation Frames, interaction timing, and component render evidence. Use when invoked as /performance for a slow interaction, unexpected re-renders, or a measured before-and-after comparison.
improve-react
Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to…
react-flow
Expert guidance for React Flow (@xyflow/react): building interactive node-based graphs, custom nodes and edges, handles, state management, layouting, TypeScript patterns, performance optimization, and theming. Use when writing React Flow code, creating custom nodes or edges, debugging flow issues, optimizing graph…
react_developer
Comprehensive React development with performance, design, composition, and React Native patterns.