debug prod issues

debug prod issues is a skill for Claude Code, Codex from different-ai/agent-bank. It costs 21 tokens per session (2,124 once invoked), scanned A, original, MIT.

Instructions for investigating production problems in a 0 Finance application hosted on Vercel. Production means the live version users access; Vercel is the service running the application and its server functions.

In plain words
What is it for?
Use them to search Vercel logs, check whether a deployment finished, inspect environment settings, and examine production database tables and records.
Why use it?
They provide the required project scope and commands for viewing logs, checking deployments, and inspecting the production Neon database. This makes it easier to connect user-visible failures with live data or deployment state.

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/different-ai/agent-bank/debug-prod-issues
Any agent
npx skills add different-ai/agent-bank --skill debug-prod-issues
Clone the repo
git clone --depth 1 https://github.com/different-ai/agent-bank

Made for: Claude Code, Codex.

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 debug prod issues

README.md
[![agentmods](https://agentmods.dev/badge/skills/different-ai/agent-bank/debug-prod-issues.svg)](https://agentmods.dev/skills/different-ai/agent-bank/debug-prod-issues)
Your own site
<a href="https://agentmods.dev/skills/different-ai/agent-bank/debug-prod-issues"><img src="https://agentmods.dev/badge/skills/different-ai/agent-bank/debug-prod-issues.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,124 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 $0.00021 $0.02124
Opus 5 $0.00010 $0.01062
Sonnet 5 $0.00004 $0.00425
Haiku 4.5 $0.00002 $0.00212

Measured 3d ago against content hash 4afe3b8a8742, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug prod issues 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 3d 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.

3. Test with curl to see response:
.opencode/skill/debug-prod-issues/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I Do

  • Debug production issues on Vercel
  • View and filter Vercel function logs
  • Wait for deployments correctly
  • Connect to production Neon database
  • Inspect tables and data for debugging

Vercel Debugging (0 Finance)

IMPORTANT: Always use --scope prologe for the 0 Finance project:

# All Vercel commands need --scope prologe
vercel logs www.0.finance --scope prologe
vercel ls --scope prologe
vercel env ls --scope prologe

Viewing Logs

# Stream live logs (waits for new logs)
vercel logs www.0.finance --scope prologe

# Logs since a specific time
vercel logs www.0.finance --scope prologe --since 5m
vercel logs www.0.finance --scope prologe --since 1h

# Filter logs (pipe to grep)
vercel logs www.0.finance --scope prologe 2>&1 | grep -i "error"
vercel logs www.0.finance --scope prologe 2>&1 | grep "ai-email"

Note: vercel logs can be slow/hang. Use timeout or Ctrl+C if needed:

timeout 30 vercel logs www.0.finance --scope prologe --since 5m 2>&1 | head -100

Checking Deployments

# List recent deployments
vercel ls --scope prologe | head -10

# Check specific deployment status
vercel inspect <deployment-url> --scope prologe

# Get latest deployment URL
vercel ls --scope prologe 2>/dev/null | head -1

Waiting for Deployments

DO NOT just sleep and hope. Use vercel inspect --wait:

# Get the latest deployment URL
LATEST=$(vercel ls --scope prologe 2>/dev/null | head -1)

# Wait for it to be ready (up to 5 minutes)
vercel inspect "$LATEST" --scope prologe --wait --timeout 5m

# Check the status in the output:
#   status: ● Building  -> still building
#   status: ● Ready     -> deployed and live!
#   status: ● Error     -> build failed

Full workflow after pushing code:

# 1. Push your changes
git push origin main

# 2. Wait a few seconds for Vercel to pick it up
sleep 5

# 3. Get the new deployment URL
LATEST=$(vercel ls --scope prologe 2>/dev/null | head -1)
echo "Waiting for: $LATEST"

# 4. Wait for it to complete
vercel inspect "$LATEST" --scope prologe --wait --timeout 5m

# 5. Now your changes are live!

Read the full file on GitHub · 325 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. 3d ago First seen · 325 lines · 21 tokens per session scan A 4afe3b8a8742

Subscribe to this mod's changes

debug prod issues is a skill published in the GitHub repository different-ai/agent-bank (250 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 2,124 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.

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