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 commands/herry423/celltypepilot/annotategit clone --depth 1 https://github.com/HERRY423/CellTypePilotWhat 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 | $0.00016 | $0.00351 |
| Opus 5 | $0.00008 | $0.00176 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
annotate 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 yesterday.
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
Annotate
Run the full CellTypePilot annotation pipeline on pre-clustered single-cell data.
Instructions
-
Environment check — Run
celltypepilot doctorfirst. If it fails, stop and help the user install dependencies. -
Inspect data — Run
celltypepilot inspect -i <path> --jsonto auto-detect:- Species (human/mouse)
- Tissue context
- Cluster key (leiden, louvain, etc.)
- Embedding key (UMAP, tSNE)
- Layer info
-
Confirm parameters — Ask the user:
- Confirm/correct species and tissue
- Choose cluster key if multiple found
- Choose embedding key for visualization
-
Run annotation:
celltypepilot annotate \ --input <path> \ --cluster-key <key> \ --output <output_dir> \ --species <human|mouse> \ --tissue <tissue> \ --embedding-key <key> -
Present results:
- Show confidence distribution (high/medium/low/needs_review)
- Highlight critic-flagged clusters
- Point user to HTML report and methodology draft
Notes
- Input must be a pre-clustered
.h5adfile - All outputs are written to
<output_dir>/ - Use
/critic <cluster_id>to deep-review any flagged cluster - Use
/ctp-inspect <path>to re-inspect data without annotating
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.
- yesterday First seen · 47 lines · 16 tokens per session scan A 39463cd5410a
annotate is a command published in the GitHub repository HERRY423/CellTypePilot (5 stars, last pushed 8d ago), licensed MIT. It adds 16 tokens to every session and 351 once invoked, about $0.0001 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
run-demo
Run a ClawBio skill demo with built-in sample data.
list-skills
List all available ClawBio bioinformatics skills with their status and capabilities.
tile-wsi
Tile a whole-slide image with tissue detection for downstream modelling. Use for .svs/.ndpi/.mrxs slides, OpenSlide, or when the user asks about patches, tiles, or WSI preprocessing.
download-encode
Download ENCODE files (BED, FASTQ, BAM, bigWig) with MD5 verification.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.