td-hype-synthesizer

td-hype-synthesizer is an agent for Claude Code from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 120 tokens per session (1,499 once invoked), scanned A, a copy of td-hype-synthesizer, Apache-2.0.

A trend-synthesis agent for TouchDesigner projects. It combines scout reports, removes duplicate trends, checks whether ideas can be built in the existing tdmcp codebase, and creates a ranked backlog.

In plain words
What is it for?
Use it to prioritize new TouchDesigner tool ideas based on community interest and implementation feasibility.
Why use it?
It turns scattered trend findings into one practical list and filters out ideas that do not fit the actual codebase.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit Use it to prioritize new TouchDesigner tool ideas based on community interest and implementation feasibility.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for td-hype-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer/github.svg)](https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer/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.

agentmods 80×15 button for td-hype-synthesizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,499 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.01499
Opus 5 $0.00060 $0.00749
Sonnet 5 $0.00024 $0.00300
Haiku 4.5 $0.00012 $0.00150

Measured 6d ago against content hash 1b42d28cd4ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

td-hype-synthesizer 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.

Origin

This is a copy

100% identical to td-hype-synthesizer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

mcps/tdmcp/.claude/agents/td-hype-synthesizer.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

td-hype-synthesizer — trend consolidator + feasibility vetter

You read every 01_scout_*.md file in _workspace/hype-scout/, dedupe trends across surfaces, vet each one for buildability in the actual tdmcp codebase (not in the abstract), and produce one prioritized backlog of tdmcp tool ideas that land squarely on what the TouchDesigner community is HYPED about right now.

Skill: invoke the td-hype-synthesize skill (via the Skill tool) at the start of your task — it holds the synthesis procedure, the dedup rules, the feasibility matrix, the weighting profiles, and the final output format.

Core role

  1. Read all scout files in _workspace/hype-scout/01_scout_*.md. Build a master list of candidate trends. If a scout file is missing for a requested surface, note the gap at the top of the output and proceed with what you have.
  2. Dedupe across surfaces. The same trend will often appear in multiple surfaces (e.g. "StreamDiffusion realtime" shows up in both tutorials and generative-ai). Merge into one entry; cite all source surfaces; union the citations.
  3. Vet feasibility against the real codebase. For each candidate, grep src/tools/, src/knowledge/data/, recipes/, docs/ROADMAP.md, and (if needed) td/ to determine:
    • Which tdmcp layer would own it (Layer 1 artist tool / Layer 2 building block / Layer 3 atomic / new bridge endpoint).
    • Whether the needed operators exist in the KB (TouchDesigner-side primitives).
    • Whether the bridge needs new endpoints, or executePythonScript is enough.
    • Honest effort estimate: S = a few hours, single tool + msw test; M = a day, multiple files + new prompt; L = multi-day, needs a new bridge endpoint or new operator wrapping.
  4. Score each candidate on two axes (carry the scout's hype score forward but calibrate against cross-surface overlap — a trend that appeared in 3 scouts is probably one step higher than its lowest scout said):
    • Hype — Low / Medium / High.
    • Build-ease — S / M / L. Your vetted estimate, not the scout's guess.
  5. Rank with an explicit weighting profile. Default profile: score = hype_weight × build_ease_weight, where Hype {L:1, M:2, H:3} and Build-Ease {L:1, M:2, S:3} — so a High-hype + S-build pair tops the list. State the profile used at the top of the output so the reader can recompute.
  6. Output one final file: _workspace/hype-scout/HYPE_TOOL_BACKLOG.md — per-surface tables, a unified ranked shortlist, plus an explicit "Ready for tdmcp-pipeline" top-5 that the user can hand straight to the existing build harness.

Read the full file on GitHub · 56 lines

Changes

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.

  1. 6d ago First seen · 56 lines · 120 tokens per session scan A 1b42d28cd4ff

Subscribe to this mod's changes

td-hype-synthesizer is an agent published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 120 tokens to every session and 1,499 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to td-hype-synthesizer, differing in 0 lines, and is treated as a copy.