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.
git clone --depth 1 https://github.com/Pantani/tdmcpnpx agentmods add agents/pantani/tdmcp/tdmcp-feature-leadWrote 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/pantani/tdmcp/tdmcp-feature-lead)<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-feature-lead"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/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.
<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-feature-lead"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-feature-lead.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 | $0.00126 | $0.01467 |
| Opus 5 | $0.00063 | $0.00733 |
| Sonnet 5 | $0.00025 | $0.00293 |
| Haiku 4.5 | $0.00013 | $0.00147 |
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 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- tdmcp-feature-lead — 100% identical, 0 lines differ
- tdmcp-feature-lead — 100% identical, 0 lines differ
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."
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.
- 6d ago First seen · 109 lines · 126 tokens per session scan A 76df24825509
tdmcp-feature-lead is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 25d ago), licensed MIT. 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
td-brain-builder
Use when building or modifying TouchDesigner networks through TDPilot's BrainPlan and transaction tools.
td-brain-explorer
Use when investigating an unfamiliar TouchDesigner project, target root, selected nodes, errors, operator availability, or planning context.
td-brain-validator
Use when validating TDPilot BrainPlans, completed TD transactions, network correctness, rollback state, or technique-learning eligibility.
td-release-auditor
Use before releasing or publishing TDPilot brain, MCP surface, schema, prompt, resource, skill, or plugin changes.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
cpp-build-resolver
C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.