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.
git clone --depth 1 https://github.com/zamushwani/biomedical-ai-skillsWrote 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/commands/zamushwani/biomedical-ai-skills/tile-wsi)<a href="https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/tile-wsi"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/tile-wsi/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/commands/zamushwani/biomedical-ai-skills/tile-wsi"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/tile-wsi.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 | $0.00044 | $0.00420 |
| Opus 5 | $0.00022 | $0.00210 |
| Sonnet 5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
tile-wsi 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.
What it actually says
Tile the slide at $0 at a target resolution of $1 microns per pixel (default: 0.5).
Follow the computational-pathology skill. Two bugs cost the most time here:
read_region(location, level, size)mixes coordinate frames.locationis in the level 0 frame;sizeis in the target level frame. Scale the location bylevel_downsamples[level]. The failure is silent: correct shape, wrong region — and a level-0 prototype hides it entirely.- Magnification is not resolution. "40x" maps to roughly 0.23–0.28 um/px depending on scanner, so tiles cut at "40x" from two scanners sit at different physical scales and the model learns the scanner. Work in mpp.
Also:
level_downsamplesare floats (4.000122, not 4). Pick levels withget_best_level_for_downsample, never==.- Composite RGBA onto white.
.convert("RGB")composites onto black, turning unscanned area into dark tissue-coloured pixels. - Detect tissue by saturation, not intensity — glass is bright and unsaturated, while pale adipose is real signal.
- Record the tissue-fraction threshold. ">50% tissue" and ">10% tissue" are different datasets.
Report: slide mpp and vendor, level chosen, tile count, tissue fraction threshold, and tile coordinates in the level 0 frame.
If $0 is empty, ask for the slide path.
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 · 24 lines · 0 tokens per session scan A e68c8980786f
tile-wsi is a command published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 12d ago), licensed MIT. It adds 44 tokens to every session and 420 once invoked, about $0.0002 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 commands, from other repositories
read
Accepts: local PDF path, DOI, journal URL, or a pasted abstract with basic metadata.
feed
Execute all steps without asking for user confirmation at intermediate stages. Report results at the end.
critic
Deep-review a specific cluster with CellTypePilot's Annotation Critic.
ctp-inspect
Inspect single-cell data — auto-detect species, tissue, clusters, embeddings.
faostat-country-profile
Generate a food security and agricultural profile for a country.
vehicle-comparison
Side-by-side comparison of launch vehicles — cost, payload, reusability.