Borrowing it
Nothing to install: this file belongs to cardstack/boxel. 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/cardstack/boxel/main/.claude/skills/catalog-test-subset/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/catalog-test-subset)<a href="https://agentmods.dev/skills/cardstack/boxel/catalog-test-subset"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/catalog-test-subset/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/cardstack/boxel/catalog-test-subset"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/catalog-test-subset.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 | $0.00475 | $0.05537 |
| Opus 5.5 | $0.00190 | $0.02215 |
| Sonnet 5.5 | $0.00095 | $0.01107 |
| Haiku 4.5 | $0.00047 | $0.00554 |
Grade A, and why
catalog-test-subset 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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalog test subset
Catalog content lives in cardstack/boxel-catalog. The deployed catalog realm serves that repo's main. Boxel's own test stacks don't clone the catalog. They serve a pinned subset of it as the catalog realm, and tests reach those definitions through @cardstack/catalog/, just as card code does in a deployment.
The subset is declared in packages/catalog/test-subset.json:
{
"repository": "cardstack/boxel-catalog",
"revision": "<40-char boxel-catalog sha whose subset files match catalog main>",
"files": [{ "path": "realm-policy/realm-policy.gts", "reason": "…" }],
"tests": {
"host": ["<ember test --filter>"],
"realmServer": ["<TEST_FILES entry>"]
}
}
packages/catalog/scripts/sync-test-subset.ts (pnpm --dir packages/catalog catalog:test-subset) materializes it.
Where a subset definition's source lives
A definition whose file the manifest lists has exactly one source: that path in cardstack/boxel-catalog. Every change to it, however small (a template tweak, a comment, a new field), is a boxel-catalog commit, which boxel then pins.
Three places in this repo look like that source and are not. Editing any of them changes nothing that CI or a deployment runs:
| Looks like the source | What it actually is |
|---|---|
packages/base/<name>.gts |
Nothing. The definition isn't in base, and platform code and tests reference the catalog copy (@cardstack/catalog/…, e.g. realmPolicyRef in runtime-common/card-operations/policy.ts). A copy added here is a second definition that drifts from the deployed one. Base's lint:no-catalog-subset-copies, part of CI Lint, fails when a file in packages/base has a subset file's name or declares a class a subset file exports. |
packages/catalog/test-subset/<path> |
Generated and gitignored. The sync writes it from the pin, and CI re-fetches it from the pin. The sync refuses to run over a copy edited after it was written. The test guards fail when the realm serves an edited copy. |
packages/catalog/contents/<path> |
The dev stack's clone of catalog main. catalog:update pulls over it. The test guards report its copy as divergent from the pin. It is a boxel-catalog checkout, so a commit there on a branch is a real catalog change, but it's easier to work from a separate boxel-catalog checkout (below). |
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.
- 5d ago First seen · 155 lines · 475 tokens per session scan A 662d2cd94087
catalog-test-subset is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 475 tokens to every session and 5,537 once invoked, about $0.0019 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 2026-10-21.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
release-safety
Release safety rules. INVOKE WHEN: yarn release, npm publish, release canary, release packages, publishing, skip checks, skip tests. NEVER skip checks or tests without explicit permission.