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 agentmods add skills/layoutit/polycss/compat-hunternpx skills add layoutit/polycss --skill compat-huntergit clone --depth 1 https://github.com/layoutit/polycssWhat 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 | $0.00066 | $0.00974 |
| Opus 5 | $0.00033 | $0.00487 |
| Sonnet 5 | $0.00013 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
compat-hunter 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 2d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compat Hunter
Use this skill when the user wants to keep digging for parser compatibility issues without building a fixed local corpus.
Workflow
-
In the repo, prefer the reusable script:
pnpm compat-hunter -- --max-models 2000Equivalent explicit form:
pnpm --filter @layoutit/polycss-core build node .agents/skills/compat-hunter/scripts/compat-hunter.mjs --max-models 2000 -
Let the script stream remote OBJ/GLB/glTF/VOX candidates, parse each model, and discard clean files. Reports are written under
bench/results/, which is ignored by git. -
Treat these as known non-actionable unless the user asks to support them:
- glTF POINTS/LINES/LINE_LOOP/LINE_STRIP primitives.
- Required Draco or meshopt compressed primitives skipped with a warning.
- STL source-quality diagnostics that the parser already handles: degenerate triangles, repaired winding, component orientation, non-manifold/shared-edge topology, supplied-normal mismatches, malformed normals/facets, overdeclared binary triangle counts, trailing binary bytes, and ignored non-Magics binary attribute bytes.
- Empty/corrupt STL containers with no complete triangle records or no valid ASCII facets.
-
Stop and inspect anything classified as:
throwunknown-warningobj-zero-no-warningglb-zero-no-warning
-
If an actionable parser issue is found, keep the saved file under the report's
interesting/directory, add a focused parser test using that behavior, implement the smallest fix, and rerun the focused parser tests plus the hunter on the saved file or source class.
Useful Commands
Fresh Objaverse and expanded GitHub stream:
pnpm compat-hunter -- --max-models 5000 --max-bytes 10mb --timeout-ms 30000
Objaverse only, later shards:
pnpm compat-hunter -- --sources objaverse --objaverse-shards 120:220 --max-models 5000
GitHub only:
pnpm compat-hunter -- --sources github --max-models 500
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 114 lines · 66 tokens per session scan A 7407423a5cee
compat-hunter is a skill published in the GitHub repository layoutit/polycss (747 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 974 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 2026-08-30.
Other skills, from other repositories
poster-grid-inspector
Analyze a poster or layout design image to detect its underlying grid system and export grid guide overlays. Use when the user wants to (1) identify the layout grid of a poster/design image (Swiss modular, N-column, asymmetric, baseline, golden ratio, rule of thirds, diagonal, radial, freeform, etc.), (2) get detected…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…