tdmcp-feature-discovery

tdmcp-feature-discovery is a skill for Claude Code, Codex from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 197 tokens per session (1,976 once invoked), scanned A, a copy of tdmcp-feature-discovery, Apache-2.0.

A project-wide feature-discovery workflow for TouchDesigner MCP, a tool for controlling TouchDesigner through an AI assistant. It coordinates surveys of several project areas and combines them into a ranked list of new feature ideas.

In plain words
What is it for?
Use it to brainstorm, audit, or prioritize future tools, effects, controls, commands, prompts, and other capabilities.
Why use it?
It gives one consolidated view of possible improvements while removing ideas that already exist or are already planned.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it to brainstorm, audit, or prioritize future tools, effects, controls, commands, prompts, and other capabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-feature-discovery
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.

Any agent
npx skills add hybridlabor-api/bdb-dev-optimized-agent-skills --skill tdmcp-feature-discovery
Clone the repo
git clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skills

Made for: Claude Code, Codex.

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 tdmcp-feature-discovery

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-feature-discovery"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-feature-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,976 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 $0.00197 $0.01976
Opus 5 $0.00098 $0.00988
Sonnet 5 $0.00039 $0.00395
Haiku 4.5 $0.00020 $0.00198

Measured 11d ago against content hash 730a2b0f7948, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tdmcp-feature-discovery 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 11d 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 tdmcp-feature-discovery — 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/.agents/skills/tdmcp-feature-discovery/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tdmcp-feature-discovery — new-feature ideation orchestrator

Coordinate a fan-out of surveyors + one synthesizer to produce a single prioritized feature backlog for tdmcp, deduped and reconciled against the roadmap. This harness finds and ranks ideas; the tdmcp-pipeline harness builds the chosen ones. Keep the boundary crisp: discovery answers "what should we consider next?", pipeline answers "build this."

Execution mode: sub-agent fan-out → fan-in

Stage Mode Why
Survey sub-agent (fan-out, parallel) the five surveyors are fully isolated — each owns one surface, no inter-comms needed; the textbook fan-out case (mirrors the pipeline's design/build stages)
Synthesize sub-agent (×1) a single reasoning-heavy consolidation pass over result files — no producer↔reviewer loop, so no team needed

No TeamCreate here — surveys are pure result-passing via files, so sub-agents are the right tool over team overhead. All Agent calls use model: "opus".

Agent roster

Agent Type Skill Output
td-surveyor (×up to 5) custom td-feature-survey _workspace/discovery/01_survey_<surface>.md
td-synthesizer custom td-feature-synthesize _workspace/discovery/FEATURE_BACKLOG.md

The five surfaces: controls (Layer 1/2 creation & performance), library (vault + recipes + .tox/component packaging + distribution), cli (CLI/DX), ai (prompts + local-LLM copilot), td-depth (Layer 3 + bridge + operator KB).

Workflow

Phase 0 — context check (follow-up support)

  1. Check whether _workspace/discovery/ exists.
  2. Decide the run mode:
    • No _workspace/discovery/ → fresh run. Go to Phase 1.
    • Exists + user asks to refresh/deepen/re-prioritize part → partial re-run. Re-invoke only the affected surveyor(s) and/or the synthesizer, passing prior artifact paths so they refine rather than rewrite.
    • Exists + a materially new ask (e.g. post-release, new competitor) → new run. Move the old dir to _workspace/discovery_<YYYYMMDD_HHMMSS>/, then Phase 1.

Read the full file on GitHub · 92 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. 11d ago First seen · 92 lines · 197 tokens per session scan A 730a2b0f7948

Subscribe to this mod's changes

tdmcp-feature-discovery 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 197 tokens to every session and 1,976 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to tdmcp-feature-discovery, differing in 0 lines, and is treated as a copy.