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/implement-experimental-kb.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/implement-experimental-kb)<a href="https://agentmods.dev/agents/bottobot/touchdesigner-mcp-server/implement-experimental-kb"><img src="https://agentmods.dev/badge/agents/bottobot/touchdesigner-mcp-server/implement-experimental-kb/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/bottobot/touchdesigner-mcp-server/implement-experimental-kb"><img src="https://agentmods.dev/badge/agents/bottobot/touchdesigner-mcp-server/implement-experimental-kb.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 | $0.00022 | $0.00329 |
| Opus 5.5 | $0.00009 | $0.00132 |
| Sonnet 5.5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
implement-experimental-kb 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 1mo 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
Implement the Experimental Techniques Knowledge Base for the TouchDesigner MCP Server at /home/robert/Documents/TD-MCP/touchdesigner-mcp-server. Tasks: (1) Create wiki/data/experimental/ directory with 7 JSON files: glsl.json (raymarching/SDF, reaction-diffusion, feedback loops, procedural textures — include actual GLSL shader code snippets), gpu-compute.json (Script TOP buffer ops, CUDA, shared memory, GPU instancing), machine-learning.json (TouchEngine CHOP/TOP, ONNX, Stable Diffusion, MediaPipe pose, note requires TD 2022+), generative-systems.json (L-systems, cellular automata, strange attractors, Replicator COMP), audio-visual.json (FFT to geometry, granular synthesis, MIDI-driven visuals, beat detection), networking.json (OSC server/client, WebSocket DAT, NDI streaming, TDAbleton sync), python-advanced.json (asyncio in TD, tdu.Dependency patterns, threading, numpy/scipy/opencv integration). (2) Create tools/get_experimental_techniques.js — browse by category. (3) Create tools/search_experimental.js — search across all categories. (4) Create tools/get_glsl_pattern.js — get specific GLSL patterns with code. (5) Register all 3 new tools in index.js. (6) Append to CHANGELOG.md. Verify with node --check.
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.
- 1mo ago First seen · 7 lines · 22 tokens per session scan A 18bc094684a7
implement-experimental-kb is an agent published in the GitHub repository bottobot/touchdesigner-mcp-server (80 stars, last pushed 28d ago), licensed MIT. It adds 22 tokens to every session and 329 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
viz-agent
Simulation visualization specialist. Handles complex multi-step visualization tasks: rendering sequences, animation pipelines, split-view comparisons, and publication-quality figure generation. Use for tasks requiring multiple MCP tool calls in sequence.
mesh-agent
Mesh and geometry analysis specialist. Handles STL/OBJ/PLY inspection, mesh quality checks, format conversions, and geometry measurements. Use for tasks requiring mesh processing or format conversion.
au-weather-mcp-expert
Use when the user asks about Australian weather, climate, or air quality — current observations, multi-day forecasts, historical archive going back to 1940, PM2.5 / AQI, bushfire smoke checks, multi-city dashboards. Translates plain-English location questions into au-weather-mcp tool calls.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.