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.
git clone --depth 1 https://github.com/dreamrec/TDPilotWrote 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/commands/dreamrec/tdpilot/td-first-wow)<a href="https://agentmods.dev/commands/dreamrec/tdpilot/td-first-wow"><img src="https://agentmods.dev/badge/commands/dreamrec/tdpilot/td-first-wow.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00593 |
| Opus 5 | $0.00008 | $0.00296 |
| Sonnet 5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
td-first-wow 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 7d 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.
What it actually says
Build one polished, moving feedback visual in the user's TouchDesigner project, transactionally and end to end. Finish with one low-quality screenshot of the verified stable TOP. Do not use a legacy macro template.
- Connect and locate. Call
td_get_infoandtd_get_focus. On connection or authentication failure, runtd_sync_diagnose, report the concrete fix, and stop. Use the focused project root when clear; otherwise use/project1. - Define the complete intent. The result must have a visible seeded TOP source, bounded recursive feedback/decay, deliberate color, continuous non-strobing motion, a stable named TOP output, and validation for nonblack content plus temporal change. Keep it compact and tasteful.
- Ground the concept. Call
td_brain_grounddirectly with the complete intent, target root, desired output,include_memory=true, andtrace_level="summary". Read thegrounding_id, candidate cards, availability, parameter semantics, recalled evidence, and current authoring contract. - Author and review. Draft the smallest graph that covers every required
facet. Use a real source feeding the feedback/composite chain; do not create
an unseeded loop. Represent motion with a grounded, registry-valid technique,
not decorative explanation. Call
td_brain_proposewith the samegrounding_id,draft_schema_version="2", anddetail_level="summary". Fix proposal rejections or essential stripped parameters and re-propose. - Execute transactionally. Require server-recomputed complete intent
coverage and no unresolved semantic edges. Execute the accepted
plan_idwith rollback on failure. Never accept a partial or legacy macro as the finished visual. - Prove the result. Check the transaction/rollback result, final errors, stable output path, and cook health. Analyze the TOP for nonblack/nonuniform content and use metadata-only temporal analysis to prove motion. If a known assertion fails, make at most one bounded repair and revalidate; otherwise roll back and report the blocker.
- Show it. Take one screenshot of the stable output at low quality
(
quality=0.25) and include it in the response. Name the created scope, explain the signal loop in one short paragraph, give two safe parameters to explore, and state the rollback result.
Never claim success from zero TD errors, a black frame, or a static image.
Natural next steps are /td-audio-reactive and /td-explain-patch.
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.
- 7d ago First seen · 45 lines · 16 tokens per session scan A db59bd5522ed
td-first-wow is a command published in the GitHub repository dreamrec/TDPilot (11 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 593 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.
Other commands, from other repositories
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
claudecode-sounds:soundpack-create
Create a custom soundpack from your own WAV files.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.