Borrowing it
Nothing to install: this file belongs to umsachde/re-com. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/umsachde/re-com/main/.claude/skills/recom-smoke-test/SKILL.mdgit clone --depth 1 https://github.com/umsachde/re-comWrote 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/umsachde/re-com/recom-smoke-test)<a href="https://agentmods.dev/skills/umsachde/re-com/recom-smoke-test"><img src="https://agentmods.dev/badge/skills/umsachde/re-com/recom-smoke-test/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/umsachde/re-com/recom-smoke-test"><img src="https://agentmods.dev/badge/skills/umsachde/re-com/recom-smoke-test.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 | $0.00059 | $0.00697 |
| Opus 5.5 | $0.00024 | $0.00279 |
| Sonnet 5 | $0.00012 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
recom-smoke-test 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scripts/smoke_all.py is the live verification layer (PLAN.md §5) — it runs
every tool against every configured backend, against the real account, and
is the only layer that can actually check the library-exclusion guarantee and
real latency. Unit tests (pytest) cannot substitute for this; they run
against fakes and structurally cannot see a real-connection or real-account
defect (see PLAN.md §6.1 and §6.6 for two that unit tests missed and this
harness caught).
How to run it
python scripts/smoke_all.py # every configured backend
python scripts/smoke_all.py --provider spotify # just one backend
python scripts/smoke_all.py --include-writes # also exercises record_feedback (writes to the real store)
Each backend runs in its own subprocess, because RECOM_PROVIDER is read once
at import — one process cannot honestly test two backends.
How to read the result — do not treat skipped as a pass
Three invariants are checked per tool, per backend:
- returns — a non-empty result, or an explicit stated reason (e.g. "no mood index for this backend"). Silent emptiness is the failure being hunted for.
- excludes — nothing already in the library. This is the project's core
guarantee (
PLAN.md§1, "The guarantee") and a live run is the only place it can actually be tested. - within — a latency ceiling. A tool quietly taking 60s has regressed even if the songs returned are correct.
A backend with no *-mcp command configured is reported as skipped, never
as a pass — don't read a skip as "that backend is fine," it means it wasn't
tested at all. record_feedback only runs under --include-writes because it
writes to the real store; a run without that flag correctly skips it.
Baseline to compare against
The last recorded baseline (PLAN.md §7.1, 2026-09-10, warm, limit=10,
graph on) had every tool passing on both backends, with the mood/playlist-mood
path notably slower on YouTube (~27s) than the single-seed path (~5-8s) — a
slow mood-path result on YouTube is not automatically a regression; compare
against this baseline rather than an assumed flat latency ceiling. If a run
disagrees sharply with these numbers, treat it as a signal to investigate, not
noise.
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.
- 10d ago First seen · 59 lines · 59 tokens per session scan A bbb8dc88e9ad
recom-smoke-test is a skill published in the GitHub repository umsachde/re-com (0 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 697 once invoked, about $0.0002 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 2026-09-14.
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.
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.