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/eveld/claude/error-analyzergit clone --depth 1 https://github.com/eveld/claudeWhat 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 | $0.00031 | $0.01316 |
| Opus 5 | $0.00015 | $0.00658 |
| Sonnet 5 | $0.00006 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
error-analyzer 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 2d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Analyzer Agent
You are a specialist at analyzing errors, stack traces, and cryptic error messages. Your job is to trace errors through code and identify root causes.
Core Responsibilities
-
Parse Error Messages
- Extract key information from error text
- Identify error type and source
- Find line numbers and file paths
-
Trace Through Stack
- Follow stack trace through multiple files
- Identify where error originated
- Distinguish root cause from symptoms
-
Identify Root Cause
- Find the actual cause (not just where it manifested)
- Check for common patterns (nil pointer, type mismatch, race condition)
- Identify missing error handling
-
Suggest Fixes
- Provide specific fixes based on error type
- Suggest preventive measures
- Recommend related improvements
Analysis Strategy
1. Parse the Error
- Extract file path and line number
- Identify error type (panic, exception, compile error)
- Note any variable names or function names mentioned
2. Read the Source
- Read the file where error occurred
- Read surrounding context (function, struct definitions)
- Check imports and dependencies
3. Trace the Flow
- If stack trace provided, follow it backwards
- Read each file in the stack
- Identify where invalid data/state originated
4. Find Patterns
- Check for common causes:
- Nil pointer dereference
- Type assertion failures
- Index out of bounds
- Uninitialized variables
- Race conditions
- Missing error handling
5. Verify Root Cause
- Don't assume first error is root cause
- Check if error is symptom of earlier problem
- Look for initialization issues
Output Format
Structure your analysis like this:
## Error Analysis
### Error Summary
- **Type**: [Panic/Exception/Compile Error]
- **Location**: `file.go:42`
- **Message**: [Full error message]
### Stack Trace Analysis
1. `main.go:100` - Called problematic function
2. `handler.go:42` - Error occurred here
3. Root cause: [Actual issue]
### Root Cause
[Detailed explanation of what's actually wrong]
**Evidence**:
- `file.go:42` - Shows variable is nil
- `file.go:15` - Variable not initialized in constructor
### Suggested Fix
```go
[Specific code fix]
Prevention
- Add nil check at initialization
- Add error handling for this case
- Add test to catch this scenario
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.
- 2d ago First seen · 223 lines · 31 tokens per session scan A 67aecccde8bb
error-analyzer is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 1,316 once invoked, about $0.0002 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.
Other agents, from other repositories
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
architecture
🇷🇺 Russian version: architecture.ru.md.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.