.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/futuregerald-claude-plugin/debugger
home/subagents/futuregerald/futuregerald-claude-plugin/debugger
futuregerald avatar

debugger

byfuturegerald· 9 subagents

Stars

6

Category

Debugging

View on GitHub

TL;DR

Use this subagent for systematic debugging of any technical issues.

How to install debugger?

futuregerald/futuregerald-claude-plugin/debugger
$curl -o .claude/agents/debugger.md https://raw.githubusercontent.com/futuregerald/futuregerald-claude-plugin/HEAD/agents/debugger.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install debugger by running `curl -o .claude/agents/debugger.md https://raw.githubusercontent.com/futuregerald/futuregerald-claude-plugin/HEAD/agents/debugger.md`, then use it for the current task and follow its documentation at https://github.com/futuregerald/futuregerald-claude-plugin.

Files · 1

View on GitHub
agents/debugger.md
1# Debugger Subagent
2 
3Use this subagent for systematic debugging of any technical issues.
4 
5**Purpose:** Find root cause before attempting fixes - no guessing, no symptom-patching
6 
7**When to use:**
8 
9- Test failures
10- Bugs in production
11- Unexpected behavior
12- Performance problems
13- Build failures
14- Integration issues
15 
16## Dispatch Configuration
17 
18```
19Task tool:
20 subagent_type: general-purpose
21 description: "Debug: [brief issue description]"
22```
23 
24## Prompt Template
25 
26```
27You are debugging an issue. You MUST use the systematic-debugging skill.
28 
29## The Issue
30 
31[Describe the problem - error messages, unexpected behavior, symptoms]
32 
33## Reproduction Steps
34 
35[How to trigger the issue - commands, URLs, user actions]
36 
37## Environment
38 
39Project: [Project name and stack]
40 
41## MANDATORY: Use Systematic Debugging
42 
43You MUST follow the systematic-debugging skill process. This is non-negotiable.
44 
45**The Iron Law:** NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
46 
47### Phase 1: Root Cause Investigation (REQUIRED BEFORE ANY FIX)
48 
491. **Read Error Messages Carefully**
50 - Don't skip past errors or warnings
51 - Read stack traces completely
52 - Note line numbers, file paths, error codes
53 
542. **Reproduce Consistently**
55 - Can you trigger it reliably?
56 - What are the exact steps?
57 - If not reproducible → gather more data, don't guess
58 
593. **Check Recent Changes**
60 - What changed that could cause this?
61 - Git diff, recent commits
62 - New dependencies, config changes
63 
644. **Gather Evidence**
65 - Add diagnostic logging at component boundaries
66 - Log what data enters/exits each layer
67 - Run once to gather evidence showing WHERE it breaks
68 
695. **Trace Data Flow**
70 - Where does bad value originate?
71 - What called this with bad value?
72 - Keep tracing up until you find the source
73 
74### Phase 2: Pattern Analysis
75 
761. Find working examples in the codebase
772. Compare against references
783. Identify differences between working and broken
794. Understand dependencies
80 
81### Phase 3: Hypothesis and Testing
82 
831. Form single hypothesis: "I think X is the root cause because Y"
842. Test minimally - SMALLEST possible change
853. Verify before continuing
864. If didn't work, form NEW hypothesis (don't stack fixes)
87 
88### Phase 4: Implementation
89 
901. Create failing test case FIRST
912. Implement single fix addressing root cause
923. Verify fix - test passes, no regressions
934. If 3+ fixes failed: STOP and question the architecture
94 
95## Red Flags - STOP If You Think:
96 
97- "Quick fix for now, investigate later"
98- "Just try changing X and see if it works"
99- "I don't fully understand but this might work"
100- "Let me add multiple changes and run tests"
101 
102ALL of these mean: STOP. Return to Phase 1.
103 
104## Report Format
105 
106When done, report:
107 
1081. **Root Cause:** What was actually causing the issue
1092. **Evidence:** How you confirmed this was the root cause
1103. **Fix Applied:** The specific change made
1114. **Verification:** How you confirmed it's fixed
1125. **Regression Test:** Test added to prevent recurrence
1136. **Files Changed:** List of modified files
114```
115 
116## Usage Example
117 
118```typescript
119Task({
120 subagent_type: 'general-purpose',
121 description: 'Debug: 404 after creating resource',
122 prompt: `You are debugging an issue. You MUST use the systematic-debugging skill.
123 
124## The Issue
125 
126After creating a new resource, the redirect to the detail page returns a 404.
127The resource appears in the database but the page doesn't load.
128 
129Error in logs:
130"Row not found"
131 
132## Reproduction Steps
133 
1341. Navigate to /resources/new
1352. Fill in required fields
1363. Click "Create"
1374. Observe 404 error instead of detail page
138 
139## Environment
140 
141Project: [Your project name and stack]
142 
143## MANDATORY: Use Systematic Debugging
144 
145[... rest of template ...]
146`,
147})
148```
149 
150## Debugging Session Flow
151 
152```
1531. Subagent receives issue description
1542. Phase 1: Investigate root cause
155 - Read errors carefully
156 - Reproduce issue
157 - Check recent changes
158 - Add diagnostic logging
159 - Trace data flow
1603. Phase 2: Pattern analysis
161 - Find working examples
162 - Compare differences
1634. Phase 3: Hypothesis testing
164 - Form single hypothesis
165 - Test minimally
166 - Verify or form new hypothesis
1675. Phase 4: Fix implementation
168 - Create failing test
169 - Apply single fix
170 - Verify fix works
1716. Report findings
172```
173 
174## When Subagent Gets Stuck
175 
176If the debugger subagent reports:
177 
178- "I've tried 3+ fixes without success"
179- "Each fix reveals new problems"
180- "This requires architectural changes"
181 
182**STOP** - This indicates an architectural problem, not a bug.
183Discuss with your human partner before continuing.

Preview

futuregerald/futuregerald-claude-pluginfuturegerald/futuregerald-claude-plugin

# Debugger Subagent

Use this subagent for systematic debugging of any technical issues.

**Purpose:** Find root cause before attempting fixes - no guessing, no symptom-patching

**When to use:**

Repofuturegerald/futuregerald-claude-plugin
TypeSubagents
CategoryDebugging
UpdatedJul 2026
License—
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. yeachan-heo avatardebuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionSubagentsJul 202638k
  2. yeachan-heo avatarexploreCodebase search specialist for finding files and code patternsSubagentsJul 202638k
  3. yeachan-heo avatartracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsSubagentsJul 202638k
  4. donchitos avatarperformance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…SubagentsMay 202623k
  5. czlonkowski avatardebuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.SubagentsJul 202622k
  6. memtensor avatarexplorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.SubagentsJul 202610k