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/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/commands/dylanroscover/embody/run-tests)<a href="https://agentmods.dev/commands/dylanroscover/embody/run-tests"><img src="https://agentmods.dev/badge/commands/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/commands/dylanroscover/embody/run-tests"><img src="https://agentmods.dev/badge/commands/dylanroscover/embody/run-tests.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 | $0.00000 | $0.00370 |
| Opus 5.5 | $0.00000 | $0.00148 |
| Sonnet 5.5 | $0.00000 | $0.00074 |
| Haiku 4.5 | $0.00000 | $0.00037 |
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.
What it actually says
Load the /run-tests skill, then run the full Embody test suite via MCP:
- Save first, unconditionally -- call the
save_projectMCP tool. Do NOT try to decide whether there is unsaved work:project.dirtydoes not exist on TD 2025 andproject.modifiedreturns a LIST of operator paths (tens of thousands of characters) that re-populates within seconds of a successful save. That unanswerable condition is exactly why this step went unperformed for months.run_testsnow REFUSES a full run when the saved.toeis missing or over an hour old, and reports the recovery point's age on every run; passconfirm_saved=Trueonly to override that deliberately - Run via the
run_testsMCP tool (deferred runner). Do NOT callRunTestsSync()insideexecute_python: the dispatch wraps that call in an undo block, which makes the undo-guard tests fail (a block is already open) and turns the whole run into one giant Ctrl+Z step. If the MCP call dies mid-run with a server-restart error (the Envoy watchdog suites restart the server it waits on), the run continues -- pollop.unit_tests.GetResults()viaexecute_pythonuntil the totals stop moving - Report the results summary (pass/fail counts per suite)
- Always read
dev/logs/afterward -- pass or fail -- and grep forERRORandWARNING(the ring buffer only holds 200 entries) - If a specific suite or test name is provided as $ARGUMENTS, run only that:
RunTestsSync(suite_name='...')orRunTestsSync(suite_name='...', test_name='...')
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 2cfbf6bd8762
- 1mo ago First seen · 8 lines · 0 tokens per session scan A c1d802f99c82
run-tests is a command published in the GitHub repository dylanroscover/Embody (199 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 370 tokens. 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 commands, from other repositories
implement-tasks
A task implementation command that carries out the tasks in a project plan. For code, it can use TDD, a process of writing a failing test before the code that makes it pass; documents and configuration are implemented directly.
sugar-task
Create a comprehensive Sugar task with rich context and metadata.
test
Run the project test suite and report results.
CLAUDE_CODE_F090_SDK_ONLY
A software-maintenance task covering JavaScript and Python software development kits, or SDKs. An SDK is a package that helps developers use a service from their own code.
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.