agentmods.dev

cellbender-batch-pipeline

cellbender-batch-pipeline is a skill for Claude Code, Codex from GGbond-bo/MemOmics-Agent. It costs 69 tokens per session (20,410 once invoked), scanned C, original, MIT.

A batch-processing workflow for running CellBender across multiple single-cell RNA sequencing samples. CellBender is software that removes background RNA contamination.

In plain words
What is it for?
Use it to process multiple raw 10x Genomics samples with CellBender and monitor the batch pipeline.
Why use it?
It helps manage repeated cleanup runs while tracking progress and avoiding accidental restarts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 19repo changed 2d ago C scan 69 tokens original MIT

Good fit Use it to process multiple raw 10x Genomics samples with CellBender and monitor the batch pipeline.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline
View source ↗ GGbond-bo/MemOmics-Agent
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.

Any agent
npx skills add GGbond-bo/MemOmics-Agent --skill cellbender-batch-pipeline
Clone the repo
git clone --depth 1 https://github.com/GGbond-bo/MemOmics-Agent

Made for: Claude Code, Codex.

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.

agentmods badge for cellbender-batch-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline/github.svg)](https://agentmods.dev/skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline)
Your own site
<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline/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.

agentmods 80×15 button for cellbender-batch-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline"><img src="https://agentmods.dev/badge/skills/ggbond-bo/memomics-agent/cellbender-batch-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 20,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.20410
Opus 5 $0.00034 $0.10205
Sonnet 5 $0.00014 $0.04082
Haiku 4.5 $0.00007 $0.02041

Measured 2d ago against content hash 30da06731509, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

cellbender-batch-pipeline scanned grade C with 2 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.

The scan reads SKILL.md. This mod also ships 8 executable files (references/heartbeat-monitor.sh, scripts/error_scanner.py, scripts/heartbeat_v2.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **铁律**: 任何涉及**删除**的操作（`rm -rf` / `del` / 覆盖输出目录）→ 必须先向用户确认"我要删除 X 目录/文件，可以吗？"并等待明确批准。不批准 = 不删。

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(cellbender_cmd, env=env, timeout=2400)
hermes_home/skills/bioinformatics/cellbender-batch-pipeline/SKILL.md · 662 lines

How it starts

The opening of the file, as written. The whole thing — 662 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CellBender 批量样本 Pipeline

🔴 CRITICAL: AUTO-START FORBIDDEN

NEVER auto-start CellBender without the user's explicit, unambiguous request.

The agent has repeatedly made this catastrophic error: reading stale task_plan.md from a wrong session and auto-restarting CellBender pipelines. User has been furious 5+ times.

Before ANY CellBender action:

  1. Verify the task_plan.md Goal matches what the user actually said in the current conversation
  2. If Goal is a placeholder ("你是谁？") or references tasks the user never mentioned → ABORT immediately
  3. If ANY doubt about whether the user asked for CellBender → ASK, do not assume
  4. When user says "cancel" / "don't run" / "didn't ask for this" → in the SAME response (do NOT wait for the next wake-up):
    • (a) kill ALL CellBender processes (taskkill /F /PID, never /IM python.exe)
    • (b) remove pipeline scripts (run_remaining.py, _heartbeat.py, _pipeline_progress.json, _heartbeat.json, monitor_v2.log)
    • (c) IMMEDIATELY rewrite task_plan.md with Goal set to actual session tasks, all CellBender phases removed, and a ⛔ BLOCKED_KEYWORDS section explicitly listing: CellBender, Monkey, any task the user explicitly cancelled
    • ⛔ If task_plan.md is NOT rewritten NOW, the next system wake-up WILL re-read the stale task_plan and restart the pipeline — causing the user to have to say "cancel" yet again
  5. Cross-session contamination: system_log.jsonl from other sessions (memomics-1c1890da) is NOT a valid source of tasks for the current session

When to Use

  • 10+ 样本需要串行跑 CellBender（总时长 > 1 小时）
  • terminal(background=true) 进程跨对话 turn 频繁死亡
  • PyTorch 2.12 + Python 3.12 环境下 torch.save 报 weakref 错误
  • 需要无人值守跑完 + 早上看结果

⛔ 核心教训

问题 1: terminal background 不可靠

terminal(background=true, notify_on_complete=true) 在跨 turn 时可能被杀，进程列表变成空，无声死亡。

症状：跑着跑着进程没了，process(action='list') 返回空，零产出。

问题 2: torch.save weakref (CellBender 专属)

Read the full file on GitHub · 662 lines

Files

What ships with it

44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago Changed 30da06731509
  2. 9d ago First seen · 662 lines · 69 tokens per session scan C 7da46e1e9ee0

Subscribe to this mod's changes

cellbender-batch-pipeline is a skill published in the GitHub repository GGbond-bo/MemOmics-Agent (19 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 20,410 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Scientific
Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens