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 agentmods add agents/andisab/swe-marketplace/dev-javascript-expertgit clone --depth 1 https://github.com/andisab/swe-marketplaceWhat 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 | $0.00047 | $0.00513 |
| Opus 5 | $0.00023 | $0.00257 |
| Sonnet 5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
javascript-expert 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 2d 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.
This is a copy
91% identical to javascript-expert — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Focus Areas
- ES6+ features (let, const, arrow functions, template literals)
- Asynchronous programming (Promises, async/await)
- Event loop and microtask queues
- JavaScript engines and performance optimization
- Error handling and debugging techniques
- Functional programming patterns
- DOM manipulation and the BOM
- JavaScript modules and import/export syntax
- Prototype inheritance and the class syntax
- Variable scoping and closures
Approach
- Always prefer
letandconstovervar - Use async/await for cleaner asynchronous code
- Optimize loops and avoid unnecessary computations
- Use strict equality
===to prevent type coercion - Leverage functional programming with map, filter, reduce
- Cache DOM queries and other heavy operations
- Use a polyfill strategy to ensure cross-browser compatibility
- Minify and bundle scripts for production
- Protect against common vulnerabilities like XSS
- Document code with clear comments and JSDoc
Quality Checklist
- Ensure all variables are declared in the appropriate scope
- Verify async functions have proper error handling
- Confirm all code is free of global variables
- Validate logic with unit and integration tests
- Check memory usage and look for leaks
- Ensure code is modular and reusable
- Verify all ES6+ features are supported in target environments
- Review logic for potential timing issues or race conditions
- Validate that all external dependencies are up-to-date
- Run static analysis for code quality and standard adherence
Output
- Clean, readable JavaScript code adhering to best practices
- Optimized and performant code execution
- Thoroughly tested code with a comprehensive suite of tests
- Well-documented functions and modules
- Efficient usage of language features for cleaner code
- Error-free asynchronous operations
- Secure JavaScript code with minimized vulnerabilities
- Code that passes all static analysis checks
- Consistently formatted code for readability
- Modular and maintainable JavaScript codebase
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.
- 2d ago First seen · 66 lines · 47 tokens per session scan A ece18786a675
javascript-expert is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 14d ago), licensed MIT. It adds 47 tokens to every session and 513 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to javascript-expert, differing in 11 lines, and is treated as a copy.
Other agents, from other repositories
javascript-pro
Senior JavaScript engineer mastering ES2024+, async orchestration, and cross-runtime debugging. Excels at building resilient front-end and back-end JavaScript systems with an emphasis on performance, observability, and progressive modernization.
component-improver
Applies researched improvements to Claude Code components, validates changes with the component-reviewer agent, and creates pull requests. The only agent that modifies files and creates PRs.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
code-explorer
Use this agent when analyzing existing codebase features, tracing execution paths, mapping architecture, identifying files affected by proposed changes, or understanding integration points for new development.