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 chemany/Mente --skill remote-testsgit clone --depth 1 https://github.com/chemany/MenteWrote 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/chemany/mente/remote-tests)<a href="https://agentmods.dev/skills/chemany/mente/remote-tests"><img src="https://agentmods.dev/badge/skills/chemany/mente/remote-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/chemany/mente/remote-tests"><img src="https://agentmods.dev/badge/skills/chemany/mente/remote-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 | $0.00011 | $0.00191 |
| Opus 5.5 | $0.00004 | $0.00076 |
| Sonnet 5.5 | $0.00002 | $0.00038 |
| Haiku 4.5 | $0.00001 | $0.00019 |
Grade A, and why
remote-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
Some codex integration tests support a running against a remote executor. This means that when CODEX_TEST_REMOTE_ENV environment variable is set they will attempt to start an executor process in a docker container CODEX_TEST_REMOTE_ENV points to and use it in tests.
Docker container is built and initialized via ./scripts/test-remote-env.sh
Currently running remote tests is only supported on Linux, so you need to use a devbox to run them
You can list devboxes via applied_devbox ls, pick the one with codex in the name.
Connect to devbox via ssh <devbox_name>.
Reuse the same checkout of codex in ~/code/codex. Reset files if needed. Multiple checkouts take longer to build and take up more space.
Check whether the SHA and modified files are in sync between remote and local.
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 First seen · 17 lines · 11 tokens per session scan A 03891a22c1df
remote-tests is a skill published in the GitHub repository chemany/Mente (11 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 191 once invoked, about $0.0000 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.