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 run-testsgit 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/run-tests)<a href="https://agentmods.dev/skills/dylanroscover/embody/run-tests"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/run-tests/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/run-tests"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/run-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.00953 |
| Opus 5.5 | $0.00007 | $0.00381 |
| Sonnet 5.5 | $0.00004 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
run-tests 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Suite
Embody has 110+ test suites (2,500+ tests) under dev/embody/unit_tests/ covering externalization, MCP tools, TDXN format, the Envoy server/bridge/jobs, install/upgrade paths, and infrastructure. Destructive and agent tiers are segregated behind their own entry points.
The save gate (read this before a full run)
run_tests refuses a full run when the saved .toe is missing or more
than an hour old, and reports the recovery point's age on every run. Call
save_project first; pass confirm_saved=True only to deliberately accept
losing everything since the last save. A single suite (suite_name=...) is
never gated -- gating cheap frequent runs would just train callers to pass
the override reflexively.
Never gate on "is there unsaved work". project.dirty does not exist on
TD 2025 (a getattr guard silently read None and the check was off), and
project.modified returns a LIST of operator paths -- not a bool -- that
re-populates within seconds of a successful save. Both proxies have failed
here, in opposite directions. The age of the .toe on disk is the only
honest signal, which is what the gate and RunDestructiveTests both use.
Running Tests
From TouchDesigner:
op.unit_tests.RunTests() # All tests, one per frame
op.unit_tests.RunTests(suite_name='test_path_utils') # Specific suite
op.unit_tests.RunTests(suite_name='test_path_utils', test_name='test_normalizePath_backslashes_converted')
op.unit_tests.RunTestsSync() # Synchronous (blocks TD)
results = op.unit_tests.GetResults() # Get results dict
Via MCP -- use the run_tests tool, NOT RunTestsSync inside execute_python:
run_tests(background=True) # all suites -- RECOMMENDED for full runs
get_job_status(job_id='job_...') # poll; the finished record carries the summary
run_tests(suite_name='test_path_utils') # small targeted runs may stay synchronous
For a FULL run always pass background=True: it returns a job id
immediately and results park restart-proof in .embody/jobs/. The
synchronous mode holds the HTTP call open for the whole run, and the Envoy
watchdog suites restart the very server it waits on -- the call is severed
("Server force-restarted / shutting down during test run") even though the
run finishes. (Pre-job-layer fallback, still valid: poll
execute_python(code="result = op.unit_tests.GetResults()") until the
totals stop moving.)
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.
- 1mo ago Changed · +16 lines bec5e0632cd7
- 1mo ago First seen · 74 lines · 18 tokens per session scan A 92c28774a269
run-tests is a skill published in the GitHub repository dylanroscover/Embody (208 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 953 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…
testing-python
Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, async testing, and CI integration.
ganju-cli
Write, test, deploy and debug Ganju custom tools (Functions) with the ganju CLI and the @ganju/sdk handler API. Use this whenever the user works in a folder with a ganju.json, imports @ganju/sdk or defineTool, mentions @ganju/cli or any ganju command (init, link, build, test, deploy, logs, versions, rollback, secret…
repository-manager-gate-execution
Run and inspect the two-tier (fast/heavy) pre-commit gate across repos via rmgates, and validate a fix without re-running the whole wave: run to populate the durable gate ledger, retest to narrow a re-run to only the hooks the ledger last recorded failing (with automatic full-wave escalation on an all-pass), and…
elicitation-scenarios
Drive the elicitation tester's scenario catalogue over the modern protocol, where input requests arrive in the tool result and are answered from the chat.
elicitation-scenarios-legacy
Drive the elicitation tester's scenario catalogue over the legacy protocol, where the server sends elicitation requests during the call instead of returning them in the result.