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/criticgit 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 | $0.00014 | $0.00279 |
| Opus 5 | $0.00007 | $0.00139 |
| Sonnet 5 | $0.00003 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
critic 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.
What it actually says
Critic
Investigate a flagged or uncertain cluster using the Annotation Critic.
Instructions
-
Identify the target — The user should specify which cluster to review. If not specified, check the evidence table for clusters with
needs_revieworlowconfidence. -
Run critic:
celltypepilot critic \ --input <path> \ --cluster-key <key> \ --focus <cluster_id> -
Analyze the output:
- Top-5 candidate cell types with scores
- Which markers support each candidate
- Which negative markers conflict
- Doublet likelihood assessment
- Ontology consistency check
-
Present findings:
- Show the evidence for and against the current annotation
- Suggest alternative cell types if the current one is uncertain
- Recommend actions: accept, re-annotate, sub-cluster, or mark as doublet
When to use
- Critic flagged a cluster with
LOW_EVIDENCE,NEG_MARKER_CONFLICT, orPOSSIBLE_DOUBLET - User questions a specific annotation
- Confidence is
loworneeds_review - Two lineage signatures are co-expressed
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 · 39 lines · 14 tokens per session scan A 30058834bbc3
critic is a command published in the GitHub repository HERRY423/CellTypePilot (5 stars, last pushed 8d ago), licensed MIT. It adds 14 tokens to every session and 279 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.