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/0xfurai/claude-code-subagents/javascript-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWhat 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 | $0.00467 |
| Opus 5 | $0.00023 | $0.00234 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- javascript-expert — 91% identical, 11 lines differ
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 · 57 lines · 47 tokens per session scan A 9f7c31939778
javascript-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (992 stars, last pushed 10mo ago), licensed MIT. It adds 47 tokens to every session and 467 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.