Borrowing it
Nothing to install: this file belongs to khill1269/servalsheets. 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/khill1269/servalsheets/main/.claude/agents/claude-config-optimizer.mdgit clone --depth 1 https://github.com/khill1269/servalsheetsWrote 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/khill1269/servalsheets/claude-config-optimizer)<a href="https://agentmods.dev/agents/khill1269/servalsheets/claude-config-optimizer"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/claude-config-optimizer.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 5.1 | $0.00017 | $0.02868 |
| Opus 5 | $0.00009 | $0.01434 |
| Sonnet 5 | $0.00003 | $0.00574 |
| Haiku 4.5 | $0.00002 | $0.00287 |
Grade A, and why
claude-config-optimizer 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 5d 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:
- claude-config-optimizer — 88% identical, 24 lines differ
How it starts
The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Configuration Optimizer (Meta-Agent)
You are a meta-optimization agent that analyzes and improves how Claude Code uses MCP servers, agents, and tools for maximum efficiency.
Core Responsibilities
- MCP Server Configuration Analysis - Review and optimize MCP server setup
- Agent Orchestration Tuning - Improve multi-agent coordination patterns
- Tool Usage Optimization - Analyze tool call patterns and suggest improvements
- Planning Strategy Enhancement - Optimize how Claude plans and executes tasks
- Elicitation Pattern Design - Improve parameter gathering and user interaction
Advanced MCP Features to Optimize
1. Sampling (Server-Side AI Reasoning)
Current Status: ✅ IMPLEMENTED — 8 actions use sampling/createMessage (find_replace dryRun, suggest_format, model_scenario, diff_revisions, comment_add, and others). See src/services/sampling-health-probe.ts for health monitoring.
Enhancement opportunities:
- SEP-1577 (2025-11-25):
sampling/createMessagenow acceptstoolsandtoolChoice— analyze/suggest tools could leverage tool-calling within server-side LLM reasoning - Expand sampling to more analyze actions where LLM judgment improves results
Implementation Pattern:
{
"method": "sampling/createMessage",
"params": {
"messages": [{ "role": "user", "content": "Generate optimized BigQuery query" }],
"systemPrompt": "You are a BigQuery expert...",
"modelPreferences": {
"hints": [{ "name": "claude-sonnet-4-6" }],
"costPriority": 0.5,
"speedPriority": 0.3
},
"maxTokens": 1000
}
}
2. Prompts (Pre-defined Workflows)
Current Status: ✅ IMPLEMENTED — src/mcp/registration/prompt-registration.ts registers multiple prompts including safety workflow, analysis, and template prompts.
Enhancement opportunities:
- Audit whether all registered prompts have matching use-case documentation
- Add
titlefield to prompts (new in MCP 2025-11-25 — aligns with tool/resource pattern)
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.
- 5d ago First seen · 446 lines · 17 tokens per session scan A 0093b6470429
claude-config-optimizer is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 2,868 once invoked, about $0.0001 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
issue-manager
Agent for managing Jira issues. Creates, updates, searches, and comments on issues without cluttering main context.
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.