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 agentmods add skills/dylanroscover/embody/externalize-operatornpx 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.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 | $0.00022 | $0.01536 |
| Opus 5 | $0.00011 | $0.00768 |
| Sonnet 5 | $0.00004 | $0.00307 |
| Haiku 4.5 | $0.00002 | $0.00154 |
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 4d 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 — 67 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 (tdn_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('tdn_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 tdn_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 tdn, 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 tdn, a drop-zone panel that toggles tdn_exclude:<par> for dragged parameters and whole-COMP tdn_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: tdn_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 at-risk content warning skips it so the check cannot contradict the export.
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.
- 4d ago First seen · 67 lines · 22 tokens per session scan A 5115d8329fc9
externalize-operator is a skill published in the GitHub repository dylanroscover/Embody (169 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,536 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 2026-08-30.
Other skills, from other repositories
test-quality
Test quality bar for this repo. Read when writing, reviewing, or designing tests — covers naming, abstraction level, assertions, determinism, and the process for agent-driven test work.
touchdesigner-self-debug
A generic workflow for self-starting TouchDesigner via computer-use (or an already-running instance), loading mcpwebserverbase.tox, and verifying any TD-side Python change (td/modules/) directly from the Textport — reading back real TD runtime values and reconciling them. Use after changing TD-side code in the…
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.
resolve-pr-comments-stack
Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack.…
split-commit-into-stack
Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…