devfix

A troubleshooting routine for the Guitar Alchemist development stack, including a Vite front end, an API server, and a Cloudflare tunnel. Vite is a development server and build tool; a 502 error means a gateway could not reach the service behind it.

In plain words
What is it for?
Use it when the demo shows a 502, the Vite server or API is down, or the user reports that the site is unreachable. It checks the relevant ports and health endpoint, reports the likely outage, and gives quick or full restart commands.
Why use it?
It quickly distinguishes whether the front end, API, or tunnel is unavailable when the demo site fails. It then points to commands for restarting the affected services.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/guitaralchemist/ga/devfix
Any agent
npx skills add GuitarAlchemist/ga --skill devfix
Clone the repo
git clone --depth 1 https://github.com/GuitarAlchemist/ga

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 621 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00000 $0.00621
Opus 5 $0.00000 $0.00311
Sonnet 5 $0.00000 $0.00124
Haiku 4.5 $0.00000 $0.00062

Measured 2d ago against content hash d60b7a33fa39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devfix scanned grade A with 1 finding 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.

Makes network callslowCapability

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

curl -s http://localhost:5176 -o /dev/null -w "%{http_code}" 2>&1 # Vite
.agent/skills/devfix/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/devfix — Emergency Dev Stack Recovery

When to use

  • Site shows 502 Bad Gateway on demos.guitaralchemist.com
  • Vite dev server is down (port 5176 not responding)
  • API server is down or unhealthy (port 5232)
  • User says "site is down", "502", "cloudflare error", "can't access demos"

What it does

Diagnoses and fixes the dev stack in 30 seconds:

Step 1: Diagnose

# Check what's running
curl -s http://localhost:5176 -o /dev/null -w "%{http_code}" 2>&1  # Vite
curl -s http://localhost:5232/health 2>&1                           # API
curl -s -o /dev/null -w "%{http_code}" https://demos.guitaralchemist.com 2>&1  # Tunnel

Step 2: Report

Tell the user exactly what's wrong:

  • Vite down (port 5176) → 502 on demos site. Most common issue.
  • API down (port 5232) → API calls fail, but static site may work.
  • Both down → Full outage.
  • Tunnel down (cloudflared not running) → Rare. Check Get-Process cloudflared.

Step 3: Fix

Tell the user to run ONE of these:

Quick fix (Vite only):

! cd ReactComponents/ga-react-components && npx vite --host --port 5176

Full fix (Vite + API):

! pwsh Scripts/start-dev.ps1

Nuclear option (everything including Aspire):

! pwsh Scripts/start-all.ps1 -NoBuild -Dashboard

Step 4: Verify

# Wait 10s then check
curl -s -o /dev/null -w "%{http_code}" https://demos.guitaralchemist.com

Architecture

  • Cloudflare Tunnel (cloudflared) → routes demos.guitaralchemist.com to localhost:5176
  • Vite (port 5176) → serves React frontend, proxies /api/* to localhost:5232
  • GaApi (port 5232) → .NET backend
  • Tunnel process usually survives reboots (Windows service), but Vite/API don't auto-restart

Common causes of 502

  1. Vite crashed or was never started after a reboot
  2. npm run build killed the dev server process
  3. Port conflict (another process on 5176)
  4. Windows update restarted the machine

Do NOT

  • Don't restart cloudflared unless the tunnel itself is broken
  • Don't run start-all.ps1 with -Dashboard unless Aspire is needed
  • Don't rebuild — use -NoBuild flag for speed

Read the full file on GitHub · 68 lines

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. 2d ago First seen · 68 lines · 0 tokens per session scan A d60b7a33fa39

Subscribe to this mod's changes

devfix is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 621 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens