Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/iwritec0de/app-devnpx agentmods add skills/iwritec0de/app-dev/js-debuggingWrote 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/iwritec0de/app-dev/js-debugging)<a href="https://agentmods.dev/skills/iwritec0de/app-dev/js-debugging"><img src="https://agentmods.dev/badge/skills/iwritec0de/app-dev/js-debugging/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/iwritec0de/app-dev/js-debugging"><img src="https://agentmods.dev/badge/skills/iwritec0de/app-dev/js-debugging.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 | $0.00120 | $0.05425 |
| Opus 5.5 | $0.00048 | $0.02170 |
| Sonnet 5.5 | $0.00024 | $0.01085 |
| Haiku 4.5 | $0.00012 | $0.00543 |
Grade A, and why
js-debugging 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 2mo 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 — 749 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JavaScript/TypeScript Debugging Skill for Next.js Applications
Systematic debugging methodology for JavaScript, TypeScript, and Next.js applications. Follows four phases: root cause investigation, pattern analysis, hypothesis testing, and implementation.
Critical Rules
- No fixes without root cause. Never apply a fix unless you understand WHY the error occurs. Guessing wastes time and introduces new bugs.
- Read error messages completely. The full stack trace, including the "Caused by" chain and any nested errors. Do not stop at the first line.
- Check BOTH browser console AND server logs. Next.js runs code on both sides. A client error may originate server-side and vice versa.
- One change at a time. Make a single change, verify the result, then proceed. Batching changes makes it impossible to know what worked.
- Always create a failing test before fixing. If you cannot reproduce it in a test, you do not understand it well enough to fix it.
Phase 1: Root Cause Investigation (JS/TS-Specific)
Reading JavaScript Stack Traces
Stack traces are read top-to-bottom. The top frame is where the error was thrown; the bottom is where execution began.
TypeError: Cannot read properties of undefined (reading 'map')
at UserList (src/components/UserList.tsx:14:23) ← Error thrown here
at renderWithHooks (react-dom.development.js:149)
at mountIndeterminateComponent (react-dom.development.js:258)
at beginWork (react-dom.development.js:312)
Key steps:
- Look at the first frame that references YOUR code (not library code).
- Check the file, line number, and column number. With source maps enabled, these map to your original TypeScript.
- For async stack traces, look for
asyncframes and the... X more framessections — these often contain the real origin.
Checking Browser DevTools Console
Open DevTools (Cmd+Option+I) and check the Console tab:
- Red errors are runtime exceptions
- Yellow warnings often indicate React-specific issues (key prop, deprecated APIs)
- Check the "Preserve log" checkbox to retain errors across navigations
- Filter by "Errors" to cut through noise
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.
- 2mo ago First seen · 749 lines · 120 tokens per session scan A 687b5c7bcf4e
js-debugging is a skill published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 7mo ago), licensed MIT. It adds 120 tokens to every session and 5,425 once invoked, about $0.0005 per session on Opus 5.5. 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.
js-debugging compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| js-debuggingiwritec0de/app-dev | Skill | 3 | 7mo ago | MIT | A | 120 | Claude Code |
| shiny-py-optimizeposit-dev/skills | Skill | 567 | 5d ago | MIT | A | 105 | Claude Code |
| shiny-r-optimizeposit-dev/skills | Skill | 567 | 5d ago | MIT | A | 105 | Claude Code |
| auditoliver-kriska/claude-elixir-phoenix | Skill | 576 | 4d ago | MIT | A | 35 | Claude Code |
| health-checkbitwize-music-studio/claude-ai-music-skills | Skill | 672 | 3d ago | CC0-1.0 | A | 38 | Claude Code |
| investigateoliver-kriska/claude-elixir-phoenix | Skill | 576 | 4d ago | MIT | A | 51 | Claude Code |
| narrow-bare-rescueoliver-kriska/claude-elixir-phoenix | Skill | 576 | 4d ago | MIT | A | 40 | Claude Code |