subagent-driven-analysis

subagent-driven-analysis is a skill for Claude Code, Codex from zpower426/datapowers. It costs 35 tokens per session (1,713 once invoked), scanned A, original, MIT.

A workflow for carrying out an analysis plan by assigning each mostly independent task to a new subagent, then reviewing its result for statistical correctness and code quality.

In plain words
What is it for?
Use it to execute multi-step analysis plans where tasks can be handled independently and checked one by one.
Why use it?
It keeps separate tasks focused and reduces confusion from carrying too much unrelated context between them. The reviews help catch incorrect analysis and coding problems before moving on.

Skill for Claude CodeCodex

Part of the datapowers plugin — 20 skills, 3 commands, 3 agents, 1 hook shipped together

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.

agentmods
npx agentmods add skills/zpower426/datapowers/subagent-driven-analysis
Any agent
npx skills add zpower426/datapowers --skill subagent-driven-analysis
Clone the repo
git clone --depth 1 https://github.com/zpower426/datapowers

Made for: Claude Code, Codex.

Or install datapowers, the plugin that ships this one along with the rest of its 20 skills, 3 commands, 3 agents, 1 hook.

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 subagent-driven-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/zpower426/datapowers/subagent-driven-analysis.svg)](https://agentmods.dev/skills/zpower426/datapowers/subagent-driven-analysis)
Your own site
<a href="https://agentmods.dev/skills/zpower426/datapowers/subagent-driven-analysis"><img src="https://agentmods.dev/badge/skills/zpower426/datapowers/subagent-driven-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.01713
Opus 5 $0.00017 $0.00856
Sonnet 5 $0.00007 $0.00343
Haiku 4.5 $0.00003 $0.00171

Measured 4d ago against content hash 1648539ca88e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-driven-analysis 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 4d 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.

skills/subagent-driven-analysis/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Analysis

Execute analysis plans by dispatching fresh subagents per task. Two-stage review after each task: statistical correctness first, then code quality.

Why subagents: Each analysis task gets a fresh agent with only the context it needs. This prevents context pollution between tasks, keeps each agent focused, and produces independently reviewable outputs.

When to Use

digraph when {
    "Have an analysis plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "subagent-driven-analysis" [shape=box];
    "executing-plans manually" [shape=box];
    "Brainstorm + write plan first" [shape=box];

    "Have an analysis plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have an analysis plan?" -> "Brainstorm + write plan first" [label="no"];
    "Tasks mostly independent?" -> "subagent-driven-analysis" [label="yes"];
    "Tasks mostly independent?" -> "executing-plans manually" [label="no, tightly coupled"];
}

The Process

digraph process {
    "Read plan, extract all tasks, create TodoWrite" [shape=box];
    "More tasks?" [shape=diamond];
    "Dispatch analyst subagent" [shape=box];
    "Subagent needs context?" [shape=diamond];
    "Provide context, re-dispatch" [shape=box];
    "Subagent completes task" [shape=box];
    "Dispatch statistical reviewer" [shape=box];
    "Statistical review passes?" [shape=diamond];
    "Subagent fixes issues" [shape=box];
    "Dispatch code quality reviewer" [shape=box];
    "Code quality passes?" [shape=diamond];
    "Mark task complete" [shape=box];
    "Final analysis review" [shape=box];
    "Done" [shape=doublecircle];

    "Read plan, extract all tasks, create TodoWrite" -> "More tasks?";
    "More tasks?" -> "Dispatch analyst subagent" [label="yes"];
    "More tasks?" -> "Final analysis review" [label="no"];
    "Dispatch analyst subagent" -> "Subagent needs context?";
    "Subagent needs context?" -> "Provide context, re-dispatch" [label="yes"];
    "Provide context, re-dispatch" -> "Dispatch analyst subagent";
    "Subagent needs context?" -> "Subagent completes task" [label="no"];
    "Subagent completes task" -> "Dispatch statistical reviewer";
    "Dispatch statistical reviewer" -> "Statistical review passes?";
    "Statistical review passes?" -> "Subagent fixes issues" [label="no"];
    "Subagent fixes issues" -> "Dispatch statistical reviewer" [label="re-review"];
    "Statistical review passes?" -> "Dispatch code quality reviewer" [label="yes"];
    "Dispatch code quality reviewer" -> "Code quality passes?";
    "Code quality passes?" -> "Subagent fixes issues" [label="no"];
    "Subagent fixes issues" -> "Dispatch code quality reviewer" [label="re-review"];
    "Code quality passes?" -> "Mark task complete" [label="yes"];
    "Mark task complete" -> "More tasks?";
    "Final analysis review" -> "Done";
}

Read the full file on GitHub · 190 lines

Files

What ships with it

3 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. 4d ago First seen · 190 lines · 35 tokens per session scan A 1648539ca88e

Subscribe to this mod's changes

subagent-driven-analysis is a skill published in the GitHub repository zpower426/datapowers (1 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,713 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

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

fba-simulator

Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.

aiming-lab/AutoResearchClaw · 69 tokens

flux-analyzer

Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.

aiming-lab/AutoResearchClaw · 44 tokens

gsmm-validator

Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.

aiming-lab/AutoResearchClaw · 52 tokens

gsmm-builder

Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.

aiming-lab/AutoResearchClaw · 45 tokens

stat-result-validator

Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.

aiming-lab/AutoResearchClaw · 36 tokens