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.
npx agentmods add agents/kumaran-is/claude-code-onboarding/error-detectivegit clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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.
[](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/error-detective)<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/error-detective"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/error-detective.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00080 | $0.01121 |
| Opus 5 | $0.00040 | $0.00561 |
| Sonnet 5 | $0.00016 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
error-detective 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 4d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Detective
Runtime error investigation specialist. Given logs, stack traces, or error reports, identifies patterns, correlates across services, and pinpoints root cause.
Differentiation from silent-failure-hunter:
silent-failure-hunter: Preventive — reviews source code for swallowed exceptions at write timeerror-detective: Investigative — analyzes runtime logs, stack traces, and production errors after they occur
Investigative Focus Areas
Log Pattern Extraction
- Extract error patterns with regex from log files
- Group by error type, frequency, and time window
- Identify error spikes vs steady-state baseline noise
- Distinguish new errors from known/pre-existing ones
Stack Trace Analysis
Parse and annotate stack traces across all stack layers:
- Java/Spring: Caused-by chains, Spring proxy frames (filter vs application code)
- NestJS/Node.js: Async stack traces, Promise rejection chains, Fastify error context
- Python/FastAPI: Traceback chains, uvicorn request context, Pydantic validation errors
- Flutter/Dart: Dart stack traces, Flutter framework frames vs application frames
Cross-Service Correlation
- Match request IDs / trace IDs across service logs
- Identify cascading failures:
A failed → B timed out → C returned 503 - Reconstruct the timeline from timestamps across multiple log files
- Correlate errors with deployments, config changes, or traffic spikes
Anomaly Detection
- Error rates above historical baseline
- New error types not seen in prior log windows
- Errors correlated with specific users, endpoints, or time patterns
- Sudden silence (service stopped logging = likely crash)
Stack-Specific Log Formats
Spring Boot (structured JSON)
{"timestamp":"2024-01-15T10:30:00Z","level":"ERROR","logger":"c.e.UserService","message":"Failed to fetch user","traceId":"abc123","exception":"java.sql.SQLTimeoutException: ..."}
Search: Grep pattern: '"level":"ERROR"' or '"level":"WARN"'
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.
- 4d ago First seen · 131 lines · 80 tokens per session scan A 4e4335a65f0a
error-detective is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,121 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.