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 commands/dylanroscover/embody/run-testsgit clone --depth 1 https://github.com/dylanroscover/EmbodyWhat 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 | $0.00000 | $0.00259 |
| Opus 5 | $0.00000 | $0.00130 |
| Sonnet 5 | $0.00000 | $0.00052 |
| Haiku 4.5 | $0.00000 | $0.00026 |
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 yesterday.
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:
- If the project holds unsaved work,
project.save()first -- the saved.toeis the recovery point - 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.
- yesterday First seen · 8 lines · 0 tokens per session scan A c1d802f99c82
run-tests is a command published in the GitHub repository dylanroscover/Embody (166 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 259 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
review-pr
Command "review-pr" from modelcontextprotocol/python-sdk, covering step 1: resolve the pr, step 2: gather the diff, step 3: collect pr discussion context, step 4: find and read linked issues and step 5: analyze and validate.
pr-address
Address PR review comments on current branch.
enforce_standards
CRITICAL: Before running the code standards enforcer, we must prepare the stack properly and abort if there are merge conflicts.
icpg-bootstrap
Infer ReasonNodes from existing git commit history. One-time setup for existing codebases.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
instructions
Use the instructions command to print the CLI playbook and current server inventory for AI agents using a running 1MCP serve instance.