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/ctp-doctorgit clone --depth 1 https://github.com/HERRY423/CellTypePilotWrote 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/herry423/celltypepilot/ctp-doctor)<a href="https://agentmods.dev/commands/herry423/celltypepilot/ctp-doctor"><img src="https://agentmods.dev/badge/commands/herry423/celltypepilot/ctp-doctor.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00353 |
| Opus 5 | $0.00006 | $0.00177 |
| Sonnet 5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
ctp-doctor 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.
What it actually says
CellTypePilot Doctor
Verify that CellTypePilot is properly installed and report the capability tier.
Naming note: registered as
/ctp-doctor(not/doctor) so it does not shadow Claude Code's built-in/doctorhealth checkup. The underlying CLI check iscelltypepilot doctor.
Instructions
-
Run doctor:
celltypepilot doctor -
Interpret results:
- Core dependencies: Python version, scanpy, anndata, matplotlib — MUST all pass
- Optional dependencies: Flask (web inspector), rpy2 (Seurat .rds), etc.
- Capability tier:
full(all deps),degraded(core only), orbroken(core missing) - MCP / Literature: PubMed direct access, MCP server status
- License: Current license tier (free/academic/commercial/trial)
-
If core deps are missing:
- Tell the user to run
pip install celltypepilotorpip install -e . - Do NOT attempt annotation without passing the doctor check
- Tell the user to run
-
If optional deps are missing:
- Inform the user which features are unavailable
- Suggest
pip install celltypepilot[web]for Web Inspector - Suggest
pip install celltypepilot[seurat]for Seurat .rds support
Notes
- Run this FIRST before any annotation workflow
- The doctor check is non-destructive and fast
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 · 40 lines · 13 tokens per session scan A 946f50e43292
ctp-doctor is a command published in the GitHub repository HERRY423/CellTypePilot (5 stars, last pushed 11d ago), licensed MIT. It adds 13 tokens to every session and 353 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
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.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.