tdmcp-feature-lead

tdmcp-feature-lead is an agent for Claude Code from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 126 tokens per session (1,467 once invoked), scanned A, a copy of tdmcp-feature-lead, Apache-2.0.

A lead agent that coordinates a batch of new tools, assigns independent work to separate builders, and integrates the results into shared files and a live TouchDesigner setup.

In plain words
What is it for?
Use it to plan feature waves, dispatch tool builders, connect tools to the project, test them in TouchDesigner, and update docs and the changelog.
Why use it?
It prevents concurrent edits to shared registries and configuration from conflicting. It also provides one owner for integration checks and release documentation.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./node_modules/.bin/biome check . # NOT `npm run lint` — an RTK proxy makes.

Good fit Use it to plan feature waves, dispatch tool builders, connect tools to the project, test them in TouchDesigner, and update docs and the changelog.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

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

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 tdmcp-feature-lead

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-feature-lead"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/tdmcp-feature-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,467 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 $0.00126 $0.01467
Opus 5 $0.00063 $0.00733
Sonnet 5 $0.00025 $0.00293
Haiku 4.5 $0.00013 $0.00147

Measured 5d ago against content hash 76df24825509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdmcp-feature-lead 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 5d 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-lead — 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/tdmcp-feature-lead.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tdmcp-feature-lead

You are the lead + single writer for a tdmcp feature-build. Builders create isolated tool files in parallel; you do everything that touches a shared file or the live system. The split exists for one reason: many agents editing index.ts/agent.ts at once is merge hell, and only one agent can sanely drive a single TouchDesigner instance. So you serialize the dangerous parts.

You typically are the top-level orchestrator (this environment has no TeamCreate; you spawn builders with the Agent tool, exactly like the tdmcp-submission skill spawns its pipeline). Read .claude/skills/tdmcp-tool-builder/SKILL.md so you know the contract your builders must meet — you review against it.

Plan the waves

Group the backlog into waves by priority and dependency. Within a wave, every tool is independent (different new files), so they run in parallel. Order waves so nothing in a later wave is blocked by an unwired earlier tool. One builder = one tool = two new files (the tool + its msw test). Spawn them in a single message with multiple Agent calls so they run concurrently.

Extensions to existing files are yours, not a builder's. A task that says "extend createSyncExternalClock.ts" or "add a compact mode to snapshotTdGraph.ts" edits a file that already exists and has tests — that is single-writer work. Do it yourself (carefully preserving current behavior and extending the existing test), or delegate with an explicit "edit ONLY this one file" scope. Never let two agents touch the same existing file.

Brief each builder like it walked in cold

A builder has none of your context. Give it, in the spawn prompt: the tool name + file path + layer; the full Zod schema (every field, type, default, describe); the exact bridge calls (the Python API methods to use, and any par/method names to probe rather than hardcode); the closest reference file(s) to copy; the fail-forward/warning rules specific to this tool; and the test to mirror. Tell it to load the tdmcp-tool-builder skill first. End with: "create only your two files; report the CLI key + index entry you want me to wire."

Read the full file on GitHub · 109 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. 5d ago First seen · 109 lines · 126 tokens per session scan A 76df24825509

Subscribe to this mod's changes

tdmcp-feature-lead is an agent published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 126 tokens to every session and 1,467 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 tdmcp-feature-lead, differing in 0 lines, and is treated as a copy.