debugger Claude Code subagentA

debugger from agentworkforce/relay is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add agentworkforce/relay/.claude/agents/debugger.md@git:20260814.67b52ca

Pins git:20260814.67b52ca in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
agentworkforce/relay
Path
.claude/agents/debugger.md
Versions recorded
5
Latest version
git:20260814.67b52ca, committed Aug 14, 2026
First version recorded
Jan 22, 2026
Size
3,315 bytes
Repository stars
1,134
License
Apache-2.0

Bug investigation and root cause analysis. Use for tracking down bugs, understanding failure modes, analyzing logs, and identifying fixes.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Debugger

You are an expert debugger specializing in systematic bug investigation and root cause analysis. You methodically trace issues to their source and propose targeted fixes.

## Core Principles

### 1. Understand Before Fixing

- Reproduce the issue first
- Gather all relevant context (logs, stack traces, steps to reproduce)
- Don't guess - verify hypotheses with evidence
- Understand the full call path before making changes

### 2. Find Root Cause, Not Symptoms

- Ask "why" multiple times to dig deeper
- Look for the underlying cause, not just where it manifests
- Consider if the bug could exist elsewhere
- Check for similar patterns in the codebase

### 3. Minimal, Targeted Fixes

- Fix the bug, don't refactor the world
- Make the smallest change that solves the problem
- Avoid introducing new complexity
- Consider regression risk of the fix

### 4. Document Your Findings

- Record the investigation path for future reference
- Document what you ruled out and why
- Note any related issues discovered

## Investigation Process

1. **Reproduce** - Confirm the bug exists and is reproducible
2. **Gather Context** - Collect logs, errors, stack traces
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add agentworkforce/relay/.claude/agents/debugger.md@sha256:2c6efc75486bf2dc

The line at the top of this page pins the label git:20260814.67b52ca, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gz5lt6uutli6o5yy.svg)](https://markdownregistry.com/a/art_gz5lt6uutli6o5yy)

0 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in agentworkforce/relay/.claude/agents/debugger.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of debugger.md from somewhere else? Ask it: where did my debugger.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Jan 22, 2026 and Aug 14, 2026, about one every 51 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260814.67b52ca latest2026-08-14 67b52ca 3,315 BA view · diff
git:20260313.532b5d52026-03-13 532b5d5 3,339 BA view · diff
git:20260312.d0e1eca2026-03-12 d0e1eca 3,307 BA view · diff
git:20260220.1f22a7b2026-02-20 1f22a7b 3,267 BA view · diff
git:20260122.9b96dbd2026-01-22 9b96dbd 3,456 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (3315 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agentworkforce/relay · 1,134 stars · license Apache-2.0 · pushed 2026-11-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gz5lt6uutli6o5yy
GET https://markdownregistry.com/api/v1/resolve?ref=agentworkforce/relay/.claude/agents/debugger.md
GET https://markdownregistry.com/api/v1/blob/2c6efc75486bf2dcd072053d6fa5fc0a283c8461cd47444277da4e78bea442e7

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from agentworkforce/relay

choosing-swarm-patterns SKILL.md skill
agentworkforce/relay · .agents/skills/choosing-swarm-patterns/SKILL.md · Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration…
git:20261106.567a3d8 · audit A · 1,134 stars
creating-agent-skills SKILL.md skill
agentworkforce/relay · .agents/skills/creating-agent-skills-skill/SKILL.md · Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the…
git:20260919.270f08c · audit A · 1,134 stars
emil-design-eng SKILL.md skill
agentworkforce/relay · .agents/skills/emil-design-eng/SKILL.md · This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible…
git:20260619.f9a7ef7 · audit A · 1,134 stars
orchestrating-agent-relay SKILL.md skill
agentworkforce/relay · .agents/skills/orchestrating-agent-relay/SKILL.md · The canonical way to run agent-relay - set up the Agent Relay core with `agent-relay init` and autonomously spawn…
git:20261108.43a614d · audit A · 1,134 stars
relay-80-100-workflow SKILL.md skill
agentworkforce/relay · .agents/skills/relay-80-100-workflow/SKILL.md · Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the…
git:20260919.270f08c · audit A · 1,134 stars
review-animations SKILL.md skill
agentworkforce/relay · .agents/skills/review-animations/SKILL.md · Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy…
git:20260619.f9a7ef7 · audit A · 1,134 stars
review-fix-signoff-loop SKILL.md skill
agentworkforce/relay · .agents/skills/review-fix-signoff-loop/SKILL.md · Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context…
git:20260519.f5dd259 · audit A · 1,134 stars
setting-up-relayfile SKILL.md skill
agentworkforce/relay · .agents/skills/setting-up-relayfile/SKILL.md · Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a…
git:20260919.270f08c · audit C · 1,134 stars
using-agent-relay SKILL.md skill
agentworkforce/relay · .agents/skills/using-agent-relay/SKILL.md · Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with…
git:20261010.4722976 · audit A · 1,134 stars
writing-relayflows SKILL.md skill
agentworkforce/relay · .agents/skills/writing-relayflows/SKILL.md · Use when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is…
git:20260919.270f08c · audit A · 1,134 stars
accessibility Claude Code subagent
agentworkforce/relay · .claude/agents/accessibility.md · A11y auditing, WCAG compliance, and inclusive design review. Ensures digital content is usable by everyone.
git:20260814.67b52ca · audit A · 1,134 stars
api-designer Claude Code subagent
agentworkforce/relay · .claude/agents/api-designer.md · REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for…
git:20260814.67b52ca · audit A · 1,134 stars

Every file in agentworkforce/relay

Other files named debugger

debugger SKILL.md skill
antonbabenko/deliberation · .agents/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 187 stars
debugger SKILL.md skill
antonbabenko/deliberation · .gemini/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 187 stars
debugger SKILL.md skill
antonbabenko/deliberation · plugins/deliberation/skills/debugger/SKILL.md · Rank root-cause hypotheses and propose the smallest safe fix.
git:20261008.893bd58 · audit A · 187 stars
debugger SKILL.md skill
claude-world/director-mode-lite · skills/debugger/SKILL.md · Systematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus…
git:20260831.099306a · audit A · 80 stars
debugger SKILL.md skill
dhaupin/vant · models/public/vant/skills/vant-skill-debugger/SKILL.md · Debugging tools.
v1.0 · audit A · 16 stars
debugger SKILL.md skill
hybridlabor-api/bdb-dev-optimized-agent-skills · skills/global_config/debugger/SKILL.md · Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
git:20260912.e168019 · audit A · 8 stars
debugger SKILL.md skill
hybridlabor-api/aos · skills/global_config/debugger/SKILL.md · Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
git:20260912.e168019 · audit A · 9 stars

Browse by kind, by grade A, or by owner.