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.
npx skills add dylanroscover/Embody --skill collabgit clone --depth 1 https://github.com/dylanroscover/EmbodyWrote 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/skills/dylanroscover/embody/collab)<a href="https://agentmods.dev/skills/dylanroscover/embody/collab"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/collab/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/skills/dylanroscover/embody/collab"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/collab.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 | $0.00069 | $0.00572 |
| Opus 5.5 | $0.00028 | $0.00229 |
| Sonnet 5.5 | $0.00014 | $0.00114 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
collab 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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collaborative mode (/collab)
Embody's default posture is autonomous: take a brief, build the whole thing, verify it, report. That is the right default for "make me X" and for work handed to sub-agents. It is the wrong default when the human wants to THINK in the network: learn a technique, explore a direction, keep their own hands on the patch. TouchDesigner is a visual medium, and for that person the network is where the thinking happens; a finished network handed over skips the part they came for.
/collab switches posture for the rest of the session, or until /brief <request> or "just build it".
In this mode
- Understand before acting: restate the goal in TD terms,
get_focusfor what they are looking at,read_tdxnorquery_networkfor what exists. Ask the one question that changes the build, not five. - Read before proposing:
get_docsfor the operator or concept,describe_op_typefor its real parameters. Bring two or three options with trade-offs, not a decision. - Build ONE step at a time: one operator or one short chain, wired into the visible output (
out1with its display flag on, so they watch it live), verified (get_op_errors,capture_top), then stop and hand the next decision back. Never finish the network in one turn. - Say what the step does in one or two sentences as you make it: the operator, the parameter, why. In this mode the explanation is as much the product as the operator.
- Leave room: when they want to place, wire or tune something themselves, wait, then read the result with
get_focusandget_network_layoutinstead of redoing it. - Discipline does not relax: layout rules, error checks, performance gates and the skill prerequisites still apply to every small step.
Leaving the mode
- "Just build it" or
/brief <request>: back to autonomous. Say so, then build from a brief. - If a small step shows the plan is wrong, say that before taking the next one. In this mode the plan is theirs to change.
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.
- 19d ago First seen · 27 lines · 69 tokens per session scan A f1d448708fca
collab is a skill published in the GitHub repository dylanroscover/Embody (199 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 572 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
python-api
This skill should be used when writing, editing, or debugging Python code that runs inside TouchDesigner — scripts, expressions, DAT callbacks, Extensions, or one-off snippets passed to executepythonscript — or whenever there is uncertainty about a td class's methods, members, or module-level API. Trigger phrases…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
amazon aurora dsql
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.
x-reader
Read source URLs from X/Twitter, articles, YouTube, Bilibili, podcasts, WeChat, Xiaohongshu, Telegram, RSS, and the open web. Use when the user provides a link and wants the original content, evidence, transcript, summary, or source-grounded analysis.
debug
This skill should be used when the user runs /touchdesigner:debug or asks to debug, investigate, or find TouchDesigner node errors — trigger phrases include "debug my TouchDesigner project", "why is this node broken", "find errors in TD", "investigate node errors", "what's wrong with /project1/geo1", or "fix this…
documentation-writer
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework. Templates for tutorial / how-to / reference / explanation live under templates/.