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 chemrich/cabineteer --skill add-scenariogit clone --depth 1 https://github.com/chemrich/cabineteerWrote 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/chemrich/cabineteer/add-scenario)<a href="https://agentmods.dev/skills/chemrich/cabineteer/add-scenario"><img src="https://agentmods.dev/badge/skills/chemrich/cabineteer/add-scenario/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/chemrich/cabineteer/add-scenario"><img src="https://agentmods.dev/badge/skills/chemrich/cabineteer/add-scenario.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 | $0.00067 | $0.00907 |
| Opus 5 | $0.00034 | $0.00453 |
| Sonnet 5 | $0.00013 | $0.00181 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
add-scenario 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding an eval scenario
Scenarios are declarative data in evals/scenarios.py, registered by wrapping each in _s(...). Each Scenario has a natural-language prompt, a list of ToolCalls, and tags / difficulty for filtering.
Structure
_s(Scenario(
name="overflow_drawer_stack", # unique across the catalogue
prompt="A 600 mm cabinet with a 900 mm drawer stack — should flag overflow.",
tags=["drawer", "evaluation"], # auto-collected into ALL_TAGS; no registration needed
difficulty="standard", # basic | standard | advanced
tool_calls=[
ToolCall(
tool="evaluate_cabinet", # must be a real tool in TOOL_DISPATCH
args={"width": 600, "height": 720, "depth": 550,
"drawer_config": [[300, "drawer"], [300, "drawer"], [300, "drawer"]]},
label="evaluate an over-tall stack",
assertions=[
Assertion("summary.errors", Op.GT, 0),
Assertion("summary.pass", Op.IS_FALSE),
],
),
],
))
Assertion operators (Op)
EQ, APPROX (abs diff < 0.15), GT, GTE, LT, LTE, IN, CONTAINS, HAS_KEY, LEN_EQ, LEN_GTE, IS_TRUE, IS_FALSE, NO_ERRORS, HAS_ERROR, HAS_WARNING.
pathis a dot-walk into the tool's JSON result ("exterior.width_mm","summary.errors"). A path that doesn't resolve fails (fail-closed).HAS_KEYwith a string expected checks the dict atpathcontains that key (Assertion("files", Op.HAS_KEY, "csv")); withexpected=True/Noneit just checks the path resolves. Don't pass a key name expecting mere existence — it now really checks the key.- Prefer falsifiable assertions. Avoid tautologies like
GTE 0on a count; assert a real bound.
Context chaining (multi-call workflows)
save_as={"var": "result.path"}— store a resolved value after a successful call.context_args={"arg_name": "var"}— inject a saved value into the next call's args.arg_transforms={"arg_name": lambda v: ...}— transform a resolved value before injection (e.g. heights list →drawer_configpairs).
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 · 64 lines · 67 tokens per session scan A 74ec33b327a8
add-scenario is a skill published in the GitHub repository chemrich/cabineteer (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 67 tokens to every session and 907 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
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".
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.
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.