fullstack-debugger

fullstack-debugger is a skill for Claude Code from curiositech/some_claude_skills. It costs 94 tokens per session (3,731 once invoked), scanned C, original, MIT.

A systematic troubleshooting guide for applications built with Next.js, Cloudflare Workers, and Supabase. It covers problems such as authentication failures, caching, database access rules, cross-origin requests, and failed builds.

In plain words
What is it for?
Use it to investigate broken pages, 500, 401, or 403 errors, caching problems, CORS errors, row-level security issues, authentication failures, and deployment or build problems.
Why use it?
It helps narrow a failure to the correct layer using reproduction, logs, network behavior, and small tests instead of guesswork.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the fullstack-debugger plugin — 1 skill shipped together

Good fit Use it to investigate broken pages, 500, 401, or 403 errors, caching problems, CORS errors, row-level security issues, authentication failures, and deployment or build problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curiositech/some_claude_skills/fullstack-debugger
Install

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.

Any agent
npx skills add curiositech/some_claude_skills --skill fullstack-debugger
Clone the repo
git clone --depth 1 https://github.com/curiositech/some_claude_skills

Made for: Claude Code.

Or install fullstack-debugger, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for fullstack-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/curiositech/some_claude_skills/fullstack-debugger.svg)](https://agentmods.dev/skills/curiositech/some_claude_skills/fullstack-debugger)
Your own site
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/fullstack-debugger"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/fullstack-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,731 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.03731
Opus 5 $0.00047 $0.01865
Sonnet 5 $0.00019 $0.00746
Haiku 4.5 $0.00009 $0.00373

Measured 3d ago against content hash e7c69daf1dcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

fullstack-debugger scanned grade C with 2 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 3d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check-cors.sh, scripts/check-rls.js, scripts/diagnose.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .next node_modules/.cache tsconfig.tsbuildinfo

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}" https://YOUR-WORKER.workers.dev/health
.claude/skills/fullstack-debugger/SKILL.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fullstack Debugger

Expert debugger for modern web stacks: Next.js 15, Cloudflare Workers, Supabase, and edge deployments. Systematic, evidence-based troubleshooting.

Activation Triggers

Activate on: "debug", "not working", "broken", "error", "500 error", "401", "403", "cache issue", "CORS error", "RLS policy", "auth not working", "blank page", "hydration error", "build failed", "worker not responding"

NOT for: Feature development → language skills | Architecture → system-architect | Performance optimization → performance-engineer

Debug Philosophy

1. REPRODUCE → Can you make it fail consistently?
2. ISOLATE   → Which layer is broken?
3. EVIDENCE  → What do logs/network/state show?
4. HYPOTHESIZE → What could cause this?
5. TEST      → Validate one hypothesis at a time
6. FIX       → Minimal change that resolves issue
7. VERIFY    → Confirm fix doesn't break other things

Architecture Layers

┌─────────────────────────────────────────────────────────────┐
│                    DEBUGGING LAYERS                         │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  Layer 1: Browser/Client                                    │
│  ├── Console errors, network tab, React DevTools           │
│  ├── localStorage/sessionStorage state                     │
│  └── React Query cache state                               │
│                                                             │
│  Layer 2: Next.js Application                              │
│  ├── Server components vs client components                │
│  ├── Build output and static generation                    │
│  ├── API routes (if any)                                   │
│  └── Hydration mismatches                                  │
│                                                             │
│  Layer 3: Cloudflare Workers                               │
│  ├── Worker logs (wrangler tail)                           │
│  ├── KV cache state                                        │
│  ├── CORS headers                                          │
│  └── Rate limiting                                         │
│                                                             │
│  Layer 4: Supabase                                         │
│  ├── Auth state and JWT tokens                             │
│  ├── RLS policies (most common issue!)                     │
│  ├── Database queries and indexes                          │
│  └── Realtime subscriptions                                │
│                                                             │
│  Layer 5: External APIs                                    │
│  ├── Third-party service availability                      │
│  ├── API rate limits                                       │
│  └── Response format changes                               │
│                                                             │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 533 lines

Files

What ships with it

7 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.

Changes

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.

  1. 3d ago First seen · 533 lines · 94 tokens per session scan C e7c69daf1dcb

Subscribe to this mod's changes

fullstack-debugger is a skill published in the GitHub repository curiositech/some_claude_skills (211 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 3,731 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

printing-press-amend

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…

mvanhorn/cli-printing-press · 222 tokens

convex-performance-audit

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

openclaw/clawhub · 38 tokens

convex-insights

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

openclaw/clawhub · 45 tokens

ssl-proxy-troubleshoot

Systematic workflow for troubleshooting SSL/proxy connectivity issues with government websites.

HKUDS/OpenSpace · 20 tokens

diagnose-backend-bug

Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…

QoderAI/better-harness · 87 tokens

axiom-networking

Use when implementing or debugging ANY network connection, API call, or socket. Covers URLSession, Network.framework, NetworkConnection, connection diagnostics.

CharlesWiltgen/Axiom · 33 tokens