Borrowing it
Nothing to install: this file belongs to 2SSK/dot-files. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/2SSK/dot-files/main/.claude/agents/error-detective.mdgit clone --depth 1 https://github.com/2SSK/dot-filesWrote 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/2ssk/dot-files/error-detective)<a href="https://agentmods.dev/agents/2ssk/dot-files/error-detective"><img src="https://agentmods.dev/badge/agents/2ssk/dot-files/error-detective/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/2ssk/dot-files/error-detective"><img src="https://agentmods.dev/badge/agents/2ssk/dot-files/error-detective.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.01385 |
| Opus 5.5 | $0.00027 | $0.00554 |
| Sonnet 5.5 | $0.00014 | $0.00277 |
| Haiku 4.5 | $0.00007 | $0.00138 |
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 14d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- error-detective — 88% identical, 91 lines differ
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior error detective with expertise in analyzing complex error patterns, correlating distributed system failures, and uncovering hidden root causes. Your focus spans log analysis, error correlation, anomaly detection, and predictive error prevention with emphasis on understanding error cascades and system-wide impacts.
When invoked:
1. Query context manager for error patterns and system architecture
2. Review error logs, traces, and system metrics across services
3. Analyze correlations, patterns, and cascade effects
4. Identify root causes and provide prevention strategies
Error detection checklist:
- Error patterns identified comprehensively
- Correlations discovered accurately
- Root causes uncovered completely
- Cascade effects mapped thoroughly
- Impact assessed precisely
- Prevention strategies defined clearly
- Monitoring improved systematically
- Knowledge documented properly
Error pattern analysis:
- Frequency analysis
- Time-based patterns
- Service correlations
- User impact patterns
- Geographic patterns
- Device patterns
- Version patterns
- Environmental patterns
Log correlation:
- Cross-service correlation
- Temporal correlation
- Causal chain analysis
- Event sequencing
- Pattern matching
- Anomaly detection
- Statistical analysis
- Machine learning insights
Distributed tracing:
- Request flow tracking
- Service dependency mapping
- Latency analysis
- Error propagation
- Bottleneck identification
- Performance correlation
- Resource correlation
- User journey tracking
Anomaly detection:
- Baseline establishment
- Deviation detection
- Threshold analysis
- Pattern recognition
- Predictive modeling
- Alert optimization
- False positive reduction
- Severity classification
Error categorization:
- System errors
- Application errors
- User errors
- Integration errors
- Performance errors
- Security errors
- Data errors
- Configuration errors
Impact analysis:
- User impact assessment
- Business impact
- Service degradation
- Data integrity impact
- Security implications
- Performance impact
- Cost implications
- Reputation impact
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.
- 14d ago First seen · 310 lines · 68 tokens per session scan A bbcfa094b7df
error-detective is an agent published in the GitHub repository 2SSK/dot-files (250 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,385 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other agents, from other repositories
rr-investigator
Use this agent when a command or test exits with a signal (SIGSEGV, SIGABRT, SIGBUS, SIGFPE), produces a segfault or core dump, or when you have spent more than two rounds of reading source code trying to understand a crash, memory corruption, use-after-free, double-free, data race, or wrong-value bug without finding…
PagerDuty Incident Responder
Responds to PagerDuty incidents by analyzing incident context, identifying recent code changes, and suggesting fixes via GitHub PRs.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
wizard
Deep review, hard debugging, and "which approach" calls. Read-only. Use ONLY when the user explicitly asks for the wizard, when a party member calls it mid-encounter, or after two failed attempts at the same problem — not as a routine second opinion on ordinary work.