Borrowing it
Nothing to install: this file belongs to bottobot/touchdesigner-mcp-server. 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/bottobot/touchdesigner-mcp-server/main/.claude/agents/improve-search-agent.mdgit clone --depth 1 https://github.com/bottobot/touchdesigner-mcp-serverWrote 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/bottobot/touchdesigner-mcp-server/improve-search-agent)<a href="https://agentmods.dev/agents/bottobot/touchdesigner-mcp-server/improve-search-agent"><img src="https://agentmods.dev/badge/agents/bottobot/touchdesigner-mcp-server/improve-search-agent.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 | $0.00018 | $0.00258 |
| Opus 5 | $0.00009 | $0.00129 |
| Sonnet 5 | $0.00004 | $0.00052 |
| Haiku 4.5 | $0.00002 | $0.00026 |
Grade A, and why
improve-search-agent 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 6d 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.
What it actually says
You are improving the search capabilities of the TouchDesigner MCP Server.
Project location: /home/robert/Documents/TD-MCP/touchdesigner-mcp-server
Your tasks:
- Review the search index at /wiki/data/search-index/search-index.json and search-stats.json
- Review the search implementation in /tools/search_operators.js and /tools/search_python_api.js
- Review /wiki/operator-data-manager.js and /wiki/operator-data-python-api.js
- Review /wiki/models/search-index.js for the search model
- Identify and implement improvements:
- Add missing entries to the search index from /wiki/data/processed/ files
- Improve search relevance by adding aliases, tags, and related terms to operator data
- Add fuzzy matching or typo tolerance if not present
- Improve search result ranking/scoring
- Add category-based filtering support
- Ensure Python API entries are properly indexed
- Update search-stats.json after rebuilding the index
- Document the search improvements in code comments
Test your changes by verifying that common searches return relevant results.
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.
- 6d ago First seen · 26 lines · 18 tokens per session scan A c768ba3eb303
improve-search-agent is an agent published in the GitHub repository bottobot/touchdesigner-mcp-server (77 stars, last pushed 18d ago), licensed MIT. It adds 18 tokens to every session and 258 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 2026-08-30.
Other agents, from other repositories
polyglot-architect
Cross-language API design and binding parity.
tdmcp-bridge-engineer
You build the part of tdmcp that the isolated tool-builders cannot: the bridge vertical slice. A bridge feature crosses four layers and every layer must agree on the same shape — that cross-boundary coherence is the whole job. Load the tdmcp-bridge-endpoint skill first; it has the file-by-file pattern.
backend-analyzer
Analyze backend services, business logic, and server-side code for inefficient algorithms, blocking operations, or unnecessary computations. Use when user asks about backend performance or runs /n1-optimizer:analyze.
api-docs
Use this agent when the user asks to "document API", "write API documentation", "document endpoints", "document REST API", "document GraphQL", "create API reference", "document webhooks", or needs documentation for HTTP endpoints, API schemas, authentication flows, or API integration guides.
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.