A pre-handoff checklist for TouchDesigner projects, a visual environment for building interactive media and real-time graphics. It checks performance, errors, unsaved operators, and recent log warnings before completion.

Use it to inspect frame rate, dropped frames, CPU and GPU memory, GPU temperature, slow components, operator errors, externalization status, and recent logs.

It helps catch runtime problems and performance bottlenecks before a project is handed over. It also records a clear final verdict based on defined thresholds.

validate — Command by dylanroscover

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 commands/dylanroscover/embody/validate

Clone the repo

git clone --depth 1 https://github.com/dylanroscover/Embody

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 431 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00431
Opus 5	$0.00000	$0.00216
Sonnet 5	$0.00000	$0.00086
Haiku 4.5	$0.00000	$0.00043

Measured 2d ago against content hash 82a995262275, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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 2d 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.

.claude/commands/validate.md · 42 lines

What it actually says

Pre-handoff validation checklist. Run this before declaring a task complete.

Prerequisites

Load /mcp-tools-reference if this is the first MCP call in this session

Validation Steps

Snapshot performance: Call get_project_performance with include_hotspots=5 and record the result
Check for errors: Call get_op_errors with recurse=true on / - report any errors or warnings found
Check externalization health: Call get_externalizations - flag any dirty (unsaved) operators

Evaluate performance metrics against these thresholds:

Metric	Condition	Severity
FPS	Below `cookRate` by more than 10%	WARNING
`droppedFrames`	Greater than 0	NOTE (cumulative counter - compare against baseline if available)
`gpuMemUsedMB`	Above 80% of `totalGpuMemMB`	WARNING
`cpuMemUsedMB`	Above 4000 MB	NOTE
`gpuTemp`	Above 85 degC	WARNING

Hotspot analysis: If any of the top 5 COMPs have combinedCookTimeMs above 2.0 ms, report them as potential bottlenecks
Check logs: Read dev/logs/ for recent ERROR or WARNING entries since the task began

Verdict

Report a verdict based on the findings:
- PASS: No errors, no warnings, performance nominal
- WARN: No errors but performance warnings or dirty externalizations present
- FAIL: Errors present in the network
Include a summary table of all metrics with pass/warn/fail status for each.

Baseline Mode

If $ARGUMENTS contains "baseline", take a performance snapshot only and report the values. Do not run the full checklist - this captures a reference point for later comparison.

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.

2d ago First seen · 42 lines · 0 tokens per session scan A 82a995262275

Subscribe to this mod's changes

validate is a command published in the GitHub repository dylanroscover/Embody (166 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 431 tokens. 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 2026-08-30.

creative-coding mcp mcp-client mcp-server touchdesigner

validate

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Prerequisites

Validation Steps

Verdict

Baseline Mode

What this file has done since we first saw it

Other commands, from other repositories

review-and-fix

pr-review

frontend

code-guide

introspect

cleanup-back-to-main