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 HermeticOrmus/LibreEmbed-Claude-Code --skill verify-libre-embedgit clone --depth 1 https://github.com/HermeticOrmus/LibreEmbed-Claude-CodeWrote 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/hermeticormus/libreembed-claude-code/verify-libre-embed)<a href="https://agentmods.dev/skills/hermeticormus/libreembed-claude-code/verify-libre-embed"><img src="https://agentmods.dev/badge/skills/hermeticormus/libreembed-claude-code/verify-libre-embed/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/hermeticormus/libreembed-claude-code/verify-libre-embed"><img src="https://agentmods.dev/badge/skills/hermeticormus/libreembed-claude-code/verify-libre-embed.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 | $0.00083 | $0.01446 |
| Opus 5.5 | $0.00033 | $0.00578 |
| Sonnet 5.5 | $0.00017 | $0.00289 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
verify-libre-embed 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 11d 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.
This is a copy
91% identical to verify-libreuiux — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify LibreEmbed-Claude-Code
LibreEmbed-Claude-Code is a plugin library, not a running app: 16 plugins under plugins/, published as the libre-embed marketplace. Its user surface is the install. A user adds this repo as a plugin marketplace in Claude Code or Grok Build, installs plugins from it (or runs ./setup.sh from a clone), and then uses the skills, commands, agents and hooks those plugins bring. This skill drives that path in throwaway configs, so a proof never touches your own Claude Code config or Grok home.
Helper (executable, bash; needs claude, grok, jq and git): .grok/skills/verify-libre-embed/bin/control-libre-embed
B=.grok/skills/verify-libre-embed/bin/control-libre-embed
$B --help
$B doctor # worth driving? CLIs, head, manifests in sync
$B run # every plugins, both CLIs, prove each loaded; one JSON result
$B run --only rtos-patterns # the same for the plugins a change touched
$B run --pr 12 --expect <sha> # the same on a PR head, fetched into a scratch clone
$B install --claude --only rtos-patterns # a fresh run that keeps its clean config for the next steps
$B details rtos-patterns # component inventory in the latest run (both CLIs)
$B setup --list # ./setup.sh inside the latest run's clean configs
$B check # scripts/check.sh, the repo's one check command
$B cleanup # drop every run's scratch; the evidence stays
JSON on stdout, progress on stderr, exit 1 on any failed proof. Everything the helper writes lives under VERIFY_LIBRE_EMBED_HOME (default ~/.local/share/verify-libre-embed): runs/<stamp>-<head8>/ (or <stamp>-pr<N>-<head8>) holds scratch/ and evidence/, and runs/latest points at the newest run.
Launch
- There is no server. Launching is starting a run: a run folder with an empty Claude Code config (
CLAUDE_CONFIG_DIR) and an empty Grok home (GROK_HOME), both underscratch/. - The tree under test is the checkout the helper sits in. With
--pr Nit is a scratch clone ofrefs/pull/N/headfetched fromorigin, and--expect <sha>refuses any other head. - Claude Code adds the tree as the
libre-embedmarketplace and installs<plugin>@libre-embed. Grok adds the checkout as a marketplace named after its folder, then installs<plugin>@<folder>. - Ready when the marketplace add exits 0:
evidence/claude-marketplace-add.logandevidence/grok-marketplace-add.log(orgrok-install.log) end inexit 0. - Teardown:
runremoves its own scratch when it finishes. Afterinstall, runcleanupwhen you are done withdetailsandsetup.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 75 lines · 83 tokens per session scan A 0a89f89fb14e
verify-libre-embed is a skill published in the GitHub repository HermeticOrmus/LibreEmbed-Claude-Code (50 stars, last pushed 6d ago), licensed MIT. It adds 83 tokens to every session and 1,446 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to verify-libreuiux, differing in 25 lines, and is treated as a copy.
Other skills, from other repositories
IoT Device Testing
IoT device testing including firmware validation, protocol testing (MQTT, CoAP), power consumption testing, and over-the-air update verification.
long-build
Coordinate long Simple builds and test matrices through finite dependency scheduling, resource monitoring, cache-preserving continuation and parallel failure repair.
debug
Diagnose and repair Simple compiler, bootstrap, build or executable failures using real artifacts, independent failure collection and focused regressions.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.