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/bottobot/touchdesigner-mcp-server/validate-experimentalgit 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/validate-experimental)<a href="https://agentmods.dev/agents/bottobot/touchdesigner-mcp-server/validate-experimental"><img src="https://agentmods.dev/badge/agents/bottobot/touchdesigner-mcp-server/validate-experimental.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 | $0.00008 | $0.00323 |
| Opus 5 | $0.00004 | $0.00161 |
| Sonnet 5 | $0.00002 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
validate-experimental 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 4d 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 validating the experimental features implementation in the TouchDesigner MCP Server.
Project location: /home/robert/Documents/TD-MCP/touchdesigner-mcp-server
Tasks:
- Run: node --check tools/get_experimental_techniques.js
- Run: node --check tools/search_experimental.js
- Run: node --check tools/get_glsl_pattern.js
- Run: node --check index.js
- Verify all /wiki/data/experimental/*.json are valid JSON: node -e "const fs=require('fs'); ['glsl','gpu-compute','machine-learning','generative-systems','audio-visual','networking','python-advanced'].forEach(c => { try { JSON.parse(fs.readFileSync('wiki/data/experimental/'+c+'.json','utf8')); console.log(c+': valid'); } catch(e) { console.error(c+': INVALID - '+e.message); } })"
- Verify new operator files in /wiki/data/processed/ (feedback_top, noise_top, etc.) are valid JSON
- Check index.js registers 'get_experimental_techniques', 'search_experimental', 'get_glsl_pattern'
- Verify at least 3 experimental technique files have codeExample fields with actual code
Fix ANY issues found before completing. If a file is missing, create a minimal valid version.
Report: All experimental files created/validated, techniques count per category, fixes applied.
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.
- 4d ago First seen · 24 lines · 8 tokens per session scan A 73d7c50a88c7
validate-experimental is an agent published in the GitHub repository bottobot/touchdesigner-mcp-server (76 stars, last pushed 15d ago), licensed MIT. It adds 8 tokens to every session and 323 once invoked, about $0.0000 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
retrieval
Two retrieval backends: a lexical index built at compile time that needs no account, and Cloudflare AI Search for hybrid semantic search when you want it.
discovery
How an agent finds these surfaces without being told: the API catalog, DNS-based discovery, an agent-skills index, and the places people actually look.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.