## Summary - Add portable installation tool (`install.sh`) for cross-machine setup - Add Claude.ai export files with proper YAML frontmatter - Add multi-agent-guide v2.0 with consolidated framework template - Rename `00-claude-code-setting` → `00-our-settings-audit` (avoid reserved word) - Add YAML frontmatter to 25+ SKILL.md files for Claude Desktop compatibility ## Commits Included - `93f604a` feat: Add portable installation tool for cross-machine setup - `9b84104` feat: Add Claude.ai export for portable skill installation - `f7ab973` fix: Add YAML frontmatter to Claude.ai export files - `3fed49a` feat(multi-agent-guide): Add v2.0 with consolidated framework - `3be26ef` refactor: Rename settings-audit skill and add YAML frontmatter Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
7.8 KiB
7.8 KiB
Claude Settings Audit Guide
Purpose: Condensed reference for Claude.ai Projects Source: 00-claude-settings-audit skill Version: 1.0
Comprehensive reference for diagnosing Claude Desktop errors and optimizing context usage.
Error Quick Reference
| Error Type | Message Pattern | Category |
|---|---|---|
| Context too large | "Exceed response limit" | Input |
| Output interrupted | "Response could not be fully generated" | Output |
| Length exceeded | "Message will exceed the length limit" | Input |
| Conversation limit | "Conversation reached maximum length" | Input |
| File too large | "Files larger than 10mb" | File |
| Rate limited | "5-hour limit reached" | Usage |
| Server overload | "Unexpected capacity constraints" | Server |
| MCP failure | "Error connecting to [ServerName]" | MCP |
| Account issue | "Account has been disabled" | Account |
Quick Diagnosis Tree
Error occurred?
│
├─ BEFORE response started?
│ ├─ "Exceed response limit" → Reduce input context
│ ├─ "Length limit" → Break into smaller messages
│ ├─ "File too large" → Reduce file size or excerpt
│ ├─ "Capacity constraints" → Wait and retry
│ └─ "MCP error" → Check MCP configuration
│
├─ DURING response?
│ ├─ "Could not be fully generated" → Request smaller output
│ └─ Output suddenly stopped → Retry or chunk request
│
└─ BEFORE even sending?
├─ "5-hour limit reached" → Wait for reset
├─ "Messages left" → Near usage limit
└─ "Account disabled" → Contact support
Token Limits by Model
| Model | Context Window | Output Limit | Practical Available |
|---|---|---|---|
| Claude 3.5 Sonnet | 200K tokens | ~8K tokens | ~150K after system |
| Claude 3 Opus | 200K tokens | ~4K tokens | ~150K after system |
| Claude 3 Haiku | 200K tokens | ~4K tokens | ~160K after system |
ERROR CATEGORIES
1. Input/Context Errors
"Exceed response limit"
Causes:
- Loaded context too large (MCP tools + skills + files)
- Conversation history accumulated
- Multiple large files attached
Solutions:
- Reduce MCP servers (max 5 recommended)
- Add
serverInstructionsto all MCP servers - Start fresh conversation
- Attach file excerpts instead of full files
"Message will exceed the length limit"
Solutions:
- Break content into smaller chunks
- Summarize key sections before sending
- Start a new conversation
"Conversation reached maximum length"
Solutions:
- Start a new conversation
- Copy essential context to new chat
2. Output Errors
"Response could not be fully generated"
Causes:
- Output exceeded ~4K-8K token limit
- Safety filter triggered
- Network interruption
- Server timeout
Solutions:
- Request smaller chunks of output
- Add constraints: "In under 500 words..."
- Be more specific in scope
- Retry once before rephrasing
Prompting techniques:
- "Provide a concise summary..."
- "List the top 10..."
- "First, outline the structure"
- "Use bullet points, not paragraphs"
3. File Errors
"Files larger than 10MB"
Solutions:
- Compress file if possible
- Split into smaller files
- Extract text content only
"Message is X% over the length limit"
Solutions:
- Extract relevant excerpts only
- Summarize large documents
- Split across multiple messages
4. Usage Limit Errors
"5-hour limit reached"
Solutions:
- Wait until reset time shown
- Upgrade plan for higher limits
- Optimize prompts to use fewer tokens
"X messages left until [time]"
Solutions:
- Combine multiple questions into one
- Wait for reset
- Consider paid plan
5. Server/Capacity Errors
"Unexpected capacity constraints"
Solutions:
- Wait 2-5 minutes and retry
- Try during off-peak hours
- Check status.claude.com for incidents
HTTP Error Codes
| Code | Meaning | Solution |
|---|---|---|
| 500 | Internal Server Error | Wait and retry |
| 429 | Too Many Requests | Slow down, wait |
| 403 | Forbidden | Check account status |
| 400 | Bad Request | Check input format |
6. MCP Connection Errors
"Error connecting to [ServerName]"
Causes:
- Server not running
- Incorrect configuration
- Transport type mismatch (stdio vs HTTP)
- Authentication failure
Diagnosis steps:
-
Check server logs:
- macOS:
~/Library/Logs/Claude/mcp-server-SERVERNAME.log - Windows:
%APPDATA%\Claude\logs\mcp-server-SERVERNAME.log
- macOS:
-
Verify configuration in
claude_desktop_config.json -
Test server independently
Common fixes:
| Issue | Fix |
|---|---|
| Transport mismatch | Add "transport": "http" to config |
| Path with spaces | Use escaped paths |
| Missing env vars | Add to "env" in config |
| Server not installed | Run npm install -g first |
Critical: Restart Claude Desktop after config changes.
7. Account Errors
"Account has been disabled"
Solutions:
- Contact Anthropic support
- Review Terms of Service
- Do not create new accounts
"Error logging you in"
Solutions:
- Disable VPN
- Clear browser cache and cookies
- Try incognito window
- Check status.claude.com
8. Output Quality Issues
Output Suddenly Stops
Solutions:
- Ask "Please continue from where you stopped"
- Request smaller chunks upfront
- Be more specific in scope
Gibberish Output
Solutions:
- Simplify prompt
- Start new conversation
- Rephrase request differently
Claude Refuses to Respond
Solutions:
- Rephrase more clearly
- Explain legitimate use case
- Break into smaller requests
TOKEN BUDGET GUIDELINES
MCP Server Token Estimates
| Server | Tokens (approx) |
|---|---|
| Playwright | ~13,500 |
| Notion | ~5,000 |
| GitHub | ~18,000 |
| Filesystem | ~4,000 |
| Zapier | ~25,000+ (avoid) |
serverInstructions Pattern
Every MCP server should have:
"serverInstructions": "[Purpose]. Use for: [case1], [case2]. Keywords: [kw1], [kw2]"
Example:
"serverInstructions": "Browser automation. Use for: screenshots, page testing. Keywords: browser, DOM, screenshot"
Budget Calculator
System overhead: ~10,000 tokens (fixed)
MCP servers: [count] × ~3,000 = [estimate]
Loaded skills: [count] × ~500 = [estimate]
Project instructions: ~[estimate]
────────────────────────────────────────────
Baseline total: [sum]
Available for work: 200,000 - [sum] = [remaining]
Targets:
- Baseline: < 40,000 tokens (20%)
- Available: > 160,000 tokens (80%)
PREVENTION CHECKLIST
Context/Input
- Maximum 5 MCP servers active
- All servers have serverInstructions
- Skills under 1,000 words
- Start fresh conversations for new topics
- Files under 10MB, prefer excerpts
Output
- Break large requests into chunks
- Use specific scope in prompts
- Paginate lists (50 items max)
- Retry once before rephrasing
Usage Limits
- Monitor "messages left" warnings
- Combine related questions
- Use concise prompts
MCP Stability
- Test servers before adding
- Restart app after config changes
- Keep servers updated
General
- Check status.claude.com when issues occur
- Keep Claude Desktop updated
- Back up important conversations
CONFIGURATION LOCATIONS
Config Files
macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Windows:
%APPDATA%\Claude\claude_desktop_config.json
Log Files
macOS:
~/Library/Logs/Claude/mcp-server-SERVERNAME.log
Windows:
%APPDATA%\Claude\logs\mcp-server-SERVERNAME.log
Reference: Claude Settings Audit Skill v1.0 Last updated: 2025-02