A focused review command for one uncertain cell cluster. A cluster is a group of cells with similar measured characteristics; the command compares possible cell types using supporting and conflicting gene markers.

Use it to review flagged clusters, inspect top candidate cell types, assess doublet likelihood, check ontology consistency, and decide whether to accept, relabel, sub-cluster, or mark a cluster as a doublet.

It helps investigate weak evidence, mixed lineage signals, possible doublets, or annotations that need a closer look.

critic — Command for Claude Code by HERRY423/CellTypePilot

Install

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.

Clone the repo

git clone --depth 1 https://github.com/HERRY423/CellTypePilot

Made for: Claude Code.

Or install celltypepilot, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 hook, 3 MCP servers.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/herry423/celltypepilot/critic/github.svg)](https://agentmods.dev/commands/herry423/celltypepilot/critic)

Your own site

<a href="https://agentmods.dev/commands/herry423/celltypepilot/critic"><img src="https://agentmods.dev/badge/commands/herry423/celltypepilot/critic/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/herry423/celltypepilot/critic"><img src="https://agentmods.dev/badge/commands/herry423/celltypepilot/critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 279 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00014	$0.00279
Opus 5.5	$0.00006	$0.00112
Sonnet 5.5	$0.00003	$0.00056
Haiku 4.5	$0.00001	$0.00028

Measured 2mo ago against content hash 30058834bbc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

commands/critic.md · 39 lines

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_review or low confidence.

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, or POSSIBLE_DOUBLET
User questions a specific annotation
Confidence is low or needs_review
Two lineage signatures are co-expressed

Changes

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.

2mo ago First seen · 39 lines · 14 tokens per session scan A 30058834bbc3

Subscribe to this mod's changes

critic is a command published in the GitHub repository HERRY423/CellTypePilot (6 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 279 once invoked, about $0.0001 per session on Opus 5.5. 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.

Scientific Single-Cell agent-plugin anndata bioinformatics cell-ontology cell-type-annotation

critic next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
criticHERRY423/CellTypePilot	Command	6	2mo ago	MIT	A	14	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code