Borrowing it
Nothing to install: this file belongs to ucb-bar/merlin. 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/ucb-bar/merlin/main/.claude/skills/test-layout/SKILL.mdgit clone --depth 1 https://github.com/ucb-bar/merlinWrote 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/ucb-bar/merlin/test-layout)<a href="https://agentmods.dev/skills/ucb-bar/merlin/test-layout"><img src="https://agentmods.dev/badge/skills/ucb-bar/merlin/test-layout/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/ucb-bar/merlin/test-layout"><img src="https://agentmods.dev/badge/skills/ucb-bar/merlin/test-layout.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 | $0.00057 | $0.00496 |
| Opus 5.5 | $0.00023 | $0.00198 |
| Sonnet 5.5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
test-layout 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 15d 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
Test layout (MANDATORY)
All tests live in merlin/tests/ (the only pytest testpaths), in subsystem buckets:
| Bucket | Put tests for… |
|---|---|
kernels/ |
kernel mining/ceiling/CCA/policy/features, kernel backend |
rvv/ |
RVV codegen (rvvgen), RVV/K1 board bringup, model-on-RVV |
dse/ |
DSE tools (dse / dse_guidance / design_pressure), cost model, search, compare |
gemmini/ |
Gemmini conformance/cert, RTL checks, OOT runner, bench contract |
targetgen/ |
TargetGen synthesis + contract validation |
ir/ |
xDSL dialects, lowering/passes, dispatch, frontends, llvmlower |
runtime/ |
runtime backends (spike/zephyr/xnnpack/openblas/saturn), engine |
infra/ |
repo conventions (artifact layout, smoke / CLI smoke) |
Rules (enforced by build_tools/scripts/check_structure.py "test layout")
- Path:
merlin/tests/<bucket>/test_<area>.py. Never put atest_*.pyat themerlin/tests/root, and<bucket>must be one of the eight above (add a new bucket only by also adding it toTEST_BUCKETSincheck_structure.py). - Place a test in the subsystem folder it exercises.
- Shared inputs:
merlin/tests/fixtures/,merlin/tests/data/. - Resolve repo paths via
from merlin.common.paths import repo_root, merlin_dir— neverPath(__file__).resolve().parents[N](keeps tests location-independent).
Run: .venv/bin/python -m pytest merlin/tests (or a bucket: pytest merlin/tests/dse).
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.
- 15d ago First seen · 35 lines · 57 tokens per session scan A 75dd5f69f06d
test-layout is a skill published in the GitHub repository ucb-bar/merlin (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 496 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 2026-10-14.
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.
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.