analyze

analyze is a command for coding agents from nguyenvanduocit/research-kit. It costs 6 tokens per session (1,766 once invoked), scanned A, original, from a forked repository, MIT.

A command for examining collected research data and turning it into findings and insights. It prepares folders, templates, and notebooks for the analysis work.

In plain words
What is it for?
Use it after research execution to analyse data, create figures and tables, and record results.
Why use it?
It provides a defined analysis stage after data collection and checks whether required sources and records are available before proceeding.

Command

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 commands/nguyenvanduocit/research-kit/analyze
Clone the repo
git clone --depth 1 https://github.com/nguyenvanduocit/research-kit

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 analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/analyze.svg)](https://agentmods.dev/commands/nguyenvanduocit/research-kit/analyze)
Your own site
<a href="https://agentmods.dev/commands/nguyenvanduocit/research-kit/analyze"><img src="https://agentmods.dev/badge/commands/nguyenvanduocit/research-kit/analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,766 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.00006 $0.01766
Opus 5 $0.00003 $0.00883
Sonnet 5 $0.00001 $0.00353
Haiku 4.5 $0.00001 $0.00177

Measured 4d ago against content hash c3237a15f126, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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.

templates/commands/analyze.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Outline

This command guides the systematic analysis of collected data to generate insights and findings. Run this after /research.execute.

IMPORTANT: The setup script (scripts/bash/setup-analysis.sh) will automatically:

  • Create all necessary directories (figures/, tables/, data/results/, notebooks/)
  • Set up analysis templates and notebooks
  • Initialize tracking files
  • Verify prerequisite phases have been completed

DO NOT manually create these directories or files - let the script handle it!

  1. Quality Gate: AI Verification (after script gate passes)

    Read execution.md, sources/SOURCES_INDEX.md, and scan sources/ directory. Verify ALL of the following. If any REQUIRED check fails, STOP and report to user. User can say "skip gate" to override (log bypass in output).

    REQUIRED checks (block unless user says "skip gate"):

    • At least 20 sources downloaded locally and indexed in SOURCES_INDEX.md
    • At least 30% of sources are Tier 1 (peer-reviewed journals, official statistics, primary data)
    • Zero URL-only citations in execution.md (all citations use file:line format)
    • Data collection status documented for every source listed in methodology.md
    • Every research question has at least 3 relevant sources collected
    • Quality score documented for at least 1 dataset
    • Failed/unavailable sources documented with reasons

    Output format:

    QUALITY GATE: execute → analyze (AI Verification)
    REQUIRED: ✓/✗ [check]
    RESULT: PASSED / BLOCKED
    

    If BLOCKED: Tell user which checks failed, suggest continuing /research.execute to collect more data.

  2. Load research context:

    • Research definition from research/###-topic-name/definition.md
    • Methodology from research/###-topic-name/methodology.md
    • Execution log from research/###-topic-name/execution.md
    • Data inventory from execution phase
  3. Initialize analysis environment:

    • Create/update research/###-topic-name/analysis.md
    • Set up analysis notebooks in notebooks/
    • Load data from data/raw/ and data/processed/
    • Prepare visualization directory figures/

Read the full file on GitHub · 238 lines

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 · 238 lines · 6 tokens per session scan A c3237a15f126

Subscribe to this mod's changes

analyze is a command published in the GitHub repository nguyenvanduocit/research-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 1,766 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.