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 skills add hybridlabor-api/bdb-dev-optimized-agent-skills --skill td-hype-synthesizegit clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skillsWrote 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/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesize)<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesize"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesize/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/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesize"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-hype-synthesize.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 | $0.00116 | $0.02630 |
| Opus 5 | $0.00058 | $0.01315 |
| Sonnet 5 | $0.00023 | $0.00526 |
| Haiku 4.5 | $0.00012 | $0.00263 |
Grade A, and why
td-hype-synthesize 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 7d 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.
This is a copy
100% identical to td-hype-synthesize — 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-hype-synthesize — synthesis + feasibility vetting + ranking
This skill is loaded by the td-hype-synthesizer sub-agent. You produce exactly one file: _workspace/hype-scout/HYPE_TOOL_BACKLOG.md. You do not scout new trends.
Procedure
Step 1 — Inventory the scouts
List every _workspace/hype-scout/01_scout_*.md file:
ls _workspace/hype-scout/01_scout_*.md
Read each file end to end. Note:
- Which surfaces are present and which are missing (
SCOUT MISSING: <surface>). - Which files are tagged
PARTIAL-DUE-TO-NETWORK— propagate that into the synthesis header. - The total candidate count and per-surface tally.
Step 2 — Build the master candidate table (in memory)
Collect every entry into a working table with columns:
| Field | Source |
|---|---|
id |
new sequential (S001…) |
name |
scout's tool name |
surfaces |
list — usually one, but grow during dedup |
summary |
merged "what artists are doing" + "why hyped" |
evidence |
union of all citations |
scout_hype |
the scout's call (H/M/L) — list if multiple scouts |
scout_build_ease |
scout's guess (S/M/L) |
scout_coverage |
NOT-COVERED / PARTIAL / COVERED |
proposed_layer |
scout's suggestion |
proposed_operators |
scout's suggestion |
Step 3 — Dedupe across surfaces
Two entries collapse into one when they describe the same TouchDesigner outcome, even if the scouts framed them differently. Heuristics:
- Same suggested operators → merge.
- Same trend name (case-insensitive, allowing minor wording differences like "StreamDiffusion realtime" vs "Realtime StreamDiffusion bridge") → merge.
- Same "what artists are doing" core (one summary is a subset of another) → merge.
When merging:
surfaces= union.evidence= union (dedupe by URL).scout_hype= if all scouts agreed, keep that. If they disagreed, take the mode but annotate inline (e.g.M (showcase: H, tutorials: M)).- A trend that appeared in 3+ surfaces gets a +1 step on Hype (capped at H). Multi-surface confirmation is itself a hype signal.
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.
- 7d ago First seen · 246 lines · 116 tokens per session scan A 7b3dfb8366b0
td-hype-synthesize is a skill published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 6d ago), licensed Apache-2.0. It adds 116 tokens to every session and 2,630 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-synthesize, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ai-equipment-failure-rca-draft
A root-cause analysis draft assistant for investigating equipment failures. Root-cause analysis means looking for the underlying reason a failure happened, not only its visible symptom.
agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-performance-analyzer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.