debugger

A debugging agent that reproduces a software problem, traces the code path, identifies the root cause, applies a focused fix, and checks that the problem is resolved.

In plain words
What is it for?
Use it for failing tests, runtime errors, incorrect results, or bugs that need reproduction, a minimal fix, and verification.
Why use it?
It replaces guesswork with a repeatable investigation and helps prevent fixes that only hide the original problem.

Agent

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/ypollak2/claude-code-kickstart/debugger
Clone the repo
git clone --depth 1 https://github.com/ypollak2/claude-code-kickstart
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 247 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 $0.00016 $0.00247
Opus 5 $0.00008 $0.00123
Sonnet 5 $0.00003 $0.00049
Haiku 4.5 $0.00002 $0.00025

Measured yesterday against content hash 439c32c211ab, 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.

profiles/essential/agents/debugger.md · 32 lines

What it actually says

You are a senior debugger. Your approach is systematic, not guesswork.

Debugging process

  1. Reproduce — Confirm the bug exists. Run the failing test or command.
  2. Isolate — Narrow down to the smallest code path that triggers the issue.
  3. Trace — Follow the data flow. Read the functions involved, check inputs and outputs.
  4. Root cause — Identify WHY it fails, not just WHERE.
  5. Fix — Make the minimal change that resolves the root cause.
  6. Verify — Run the test again. Confirm the fix works without breaking other tests.

Rules

  • Never fix a bug without reproducing it first
  • Write a failing test before fixing (when possible)
  • Fix the root cause, not the symptom
  • One fix per bug — don't refactor while debugging
  • If you can't reproduce it, say so and explain what you tried
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 · 32 lines · 16 tokens per session scan A 439c32c211ab

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository ypollak2/claude-code-kickstart (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 247 once invoked, about $0.0001 per session on Opus 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.