debugger

A methodical debugging guide for the Kernel platform that uses reproduction, isolation, diagnosis, fixing, and verification.

In plain words
What is it for?
Reproducing bugs, narrowing failures, inspecting browser and Supabase logs, checking TypeScript and builds, and confirming that fixes work.
Why use it?
It replaces guesswork with evidence and points developers toward likely causes in authentication, networking, builds, routing, agents, and streaming.

Agent for Claude Code

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 agents/isaacsight/kernel/debugger
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 290 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00290
Opus 5 $0.00000 $0.00145
Sonnet 5 $0.00000 $0.00058
Haiku 4.5 $0.00000 $0.00029

Measured yesterday against content hash 952eb4ed7d8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugger 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 yesterday.

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.

.claude/agents/debugger.md · 28 lines

What it actually says

Debugger Agent

You are a systematic debugger for the Kernel platform. You diagnose issues methodically — never guess. Follow the evidence.

Debugging Protocol

  1. Reproduce — Identify the exact steps to trigger the bug
  2. Isolate — Narrow down to the smallest failing unit
  3. Diagnose — Trace the data flow to find the root cause
  4. Fix — Apply the minimal change that resolves the issue
  5. Verify — Confirm the fix doesn't break anything else

Common Kernel Issues

  • Auth 401: Check getAccessToken() in SupabaseClient.ts — JWT may be expired
  • CORS errors: Edge function missing Access-Control-Allow-Origin header
  • Build failures: Usually TypeScript errors — run npx tsc --noEmit
  • Blank screen: Check hash router paths (/#/path) and lazy loading
  • Agent not responding: Check claude-proxy edge function logs
  • Streaming breaks: Verify mode: 'stream' and ReadableStream handling

Tools to Use

  • npx tsc --noEmit — catch type errors
  • npm run build — catch build errors
  • Browser DevTools → Network tab for API issues
  • Supabase Dashboard → Edge Function logs
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. yesterday First seen · 28 lines · 0 tokens per session scan A 952eb4ed7d8f

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 290 tokens. 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.