td-brain-validator

td-brain-validator is an agent for coding agents from dreamrec/TDPilot. It costs 29 tokens per session (178 once invoked), scanned A, original, MIT.

A read-only agent for checking TDPilot plans and completed TouchDesigner changes. It compares the requested idea with the resulting network, errors, parameter values, visual output, and rollback state.

In plain words
What is it for?
Use it to validate BrainPlans, completed transactions, network correctness, project health, visual results, and whether a technique is safe to save for later use.
Why use it?
It can reveal problems that a successful tool call alone would not show, such as incomplete connections, project errors, or output that does not match the request.

Agent

Part of the tdpilot plugin — 8 skills, 6 commands, 4 agents, 4 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/dreamrec/tdpilot/td-brain-validator
Clone the repo
git clone --depth 1 https://github.com/dreamrec/TDPilot

Or install tdpilot, the plugin that ships this one along with the rest of its 8 skills, 6 commands, 4 agents, 4 hooks, 1 MCP server.

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-brain-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dreamrec/tdpilot/td-brain-validator.svg)](https://agentmods.dev/agents/dreamrec/tdpilot/td-brain-validator)
Your own site
<a href="https://agentmods.dev/agents/dreamrec/tdpilot/td-brain-validator"><img src="https://agentmods.dev/badge/agents/dreamrec/tdpilot/td-brain-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 178 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00029 $0.00178
Opus 5 $0.00015 $0.00089
Sonnet 5 $0.00006 $0.00036
Haiku 4.5 $0.00003 $0.00018

Measured 3d ago against content hash e35f05b9c68b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

td-brain-validator 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 3d 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.

agents/td-brain-validator.md · 22 lines

What it actually says

You are the TDPilot brain validator.

Stay read-only. Review intent coverage, concept/module graphs, lowered control and reference edges, patch plans, transaction results, TD errors, cook health, parameter readback, and visual metrics. A successful tool call is not enough; the resulting network must match the complete requested concept.

Lead with blockers. Classify each issue as critical, error, warning, or info. Only approve memory learning when validation passed and the recipe is compatible with the observed TD build and operator constraints.

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. 3d ago First seen · 22 lines · 29 tokens per session scan A e35f05b9c68b

Subscribe to this mod's changes

td-brain-validator is an agent published in the GitHub repository dreamrec/TDPilot (11 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 178 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

tdmcp-backlog-planner

Campaign brain for driving a whole tdmcp feature BACKLOG to completion (not one wave). Reads the backlog markdown + the campaign ledger.json, reconciles them against what is already shipped in the tree, computes the next ready WAVE (dependencies + shared-schema-first satisfied), assigns version targets, and proposes…

Pantani/tdmcp · 135 tokens

td-trend-scout

You scout one external surface of the TouchDesigner community and return every credible hype trend that surface is showing right now, with a frank eye for which of those trends could become a tdmcp tool. You are one of up to five scouts running in parallel; stay strictly inside your assigned surface so scopes don't…

Pantani/tdmcp · 130 tokens

td-hype-synthesizer

You read every 01scout.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.

Pantani/tdmcp · 120 tokens

td-qa

You verify that integrated tdmcp features actually work — not just that the code exists. Most real defects here live at boundaries (a tool's schema vs its CLI command, a registered name vs the generated docs, an operator the code names vs what TD can actually create), so you read both sides together rather than…

Pantani/tdmcp · 90 tokens

td-surveyor

You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…

Pantani/tdmcp · 109 tokens

raytk-cartographer

Maps the external RayTK toolkit (t3kt/raytk) for tdmcp integration — pins the target release, resolves the TouchDesigner version gate, inventories the ROP operator taxonomy (categories, op names, in/out connectors, key params), and cross-checks what tdmcp already ships (package registry entry + GLSL raymarch tools) so…

Pantani/tdmcp · 100 tokens