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 externalize-operatorgit 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/externalize-operator)<a href="https://agentmods.dev/skills/dylanroscover/embody/externalize-operator"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/externalize-operator/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/externalize-operator"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/externalize-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 51 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00022 | $0.01903 |
| Opus 5.5 | $0.00009 | $0.00761 |
| Sonnet 5.5 | $0.00004 | $0.00381 |
| Haiku 4.5 | $0.00002 | $0.00190 |
Grade A, and why
externalize-operator 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 24d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Externalize Operator Workflow
Tagging (includes save)
externalize_op tags the operator AND writes it to disk in one step (it calls Update() internally). No separate save is needed.
- Tag and externalize:
externalize_opon the operator (auto-detects type if omitted) - Verify:
get_externalization_statusto confirm dirty state and file path - Inspect: Verify file exists in
embody/via file inspection
Re-exporting After Changes
save_externalization force re-exports an already-externalized operator. Use it after modifying an operator in TD when you need to update its file on disk.
Excluding Runtime State from TDXN Exports (tdxn_exclude:<par> tags)
When a parameter holds runtime state (a session file path, a negotiated port, a live readout) rather than configuration, keep its value out of committed .tdxn files by tagging the operator itself - one tag per parameter, using the colon-suffixed form of the exclude tag:
op('deck_a').tags.add('tdxn_exclude:file')
The operator and its other parameters export normally; the named parameter's constant value is omitted (expressions/binds still export - references are configuration). The bare tdxn_exclude tag on a COMP is different: it makes the whole COMP invisible to TDXN. The suffixed tag round-trips in the .tdxn, so the omission is visible and survives reconstruction; it takes effect at the COMP's next export (Save tdxn, Update, or project save). A tag naming a nonexistent parameter logs a WARNING at export. Users can manage these visually: the tagger's Actions menu on a TDXN COMP has Exclude from tdxn, a drop-zone panel that toggles tdxn_exclude:<par> for dragged parameters and whole-COMP tdxn_exclude for dragged COMPs, listing every exclusion in the subtree with a per-row x to remove it.
A third form targets a DAT's live contents instead of a parameter: tdxn_exclude:dat_content (a reserved name, so it never trips the unknown-parameter warning). Use it for DATs whose rows are runtime state with no authored value -- a log ring buffer, a status readout. Those are normally force-captured even when Embed DATs is OFF, because Embody refuses to drop content that exists nowhere else on disk; this tag is the only sanctioned way past that net, so apply it only where losing the content is the intent. The operator itself still exports in full (parameters, position, wiring, tags) and returns empty on reconstruction, and the save-time content check reads the same rule, so it never flags the DAT or files it as its own file.
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.
- 24d ago Changed ef762b0ea343
- 1mo ago Changed · +9 lines 6d75ab685950
- 1mo ago Changed 69c972934d34
- 1mo ago Changed c0bcb2ff2a1b
- 1mo ago First seen · 67 lines · 22 tokens per session scan A 5115d8329fc9
externalize-operator is a skill published in the GitHub repository dylanroscover/Embody (208 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,903 once invoked, about $0.0001 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 2026-08-30.
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…
issue_approve
Approve issue to transition to next workflow status.
metagit-cli
CLI-only shortcuts for metagit agents — workspace catalog, discovery, prompts, sync, layout, and config. Use instead of MCP or HTTP API when operating from a shell or agentmode session.
nextcloud-files
Browse and manage Nextcloud files and folders over WebDAV via the nextcloud-agent MCP server — list a directory, read/download a file, upload, create/delete/move/copy, and read properties. Use when the agent must navigate a Nextcloud file tree, fetch a document's bytes, or reorganize storage. Do NOT use for sharing…
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…