analyze-only

analyze-only is a command for Cursor from codeready-toolchain/tarsy. It costs 0 tokens per session (216 once invoked), scanned A, original, Apache-2.0.

A command for investigating code, architecture, or a technical problem and giving recommendations without changing files. It can inspect implementations, data flow, dependencies, and related code.

In plain words
What is it for?
Use it for code reviews, technical investigations, tracing behavior, identifying concerns, and producing recommendations with file and line references.
Why use it?
It separates diagnosis from implementation, so you can understand the current situation and possible solutions before making changes.

Command for Cursor

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/codeready-toolchain/tarsy/analyze-only
Clone the repo
git clone --depth 1 https://github.com/codeready-toolchain/tarsy

Made for: Cursor.

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-only

README.md
[![agentmods](https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/analyze-only.svg)](https://agentmods.dev/commands/codeready-toolchain/tarsy/analyze-only)
Your own site
<a href="https://agentmods.dev/commands/codeready-toolchain/tarsy/analyze-only"><img src="https://agentmods.dev/badge/commands/codeready-toolchain/tarsy/analyze-only.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 216 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 $0.00000 $0.00216
Opus 5 $0.00000 $0.00108
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00022

Measured 5d ago against content hash 76f3fcd346b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-only 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.

.cursor/commands/analyze-only.md · 32 lines

What it actually says

Comprehensive Analysis Only

DO NOT CHANGE ANY CODE. Perform analysis and provide recommendations only.

When the user later asks to implement (e.g., "do it", "implement this", "proceed"), then make the changes directly. Don't ask for confirmation, but DO ask clarifying questions if there's genuine uncertainty about what or how to implement.


Analysis Guidelines

Perform a thorough investigation of the requested topic, codebase area, or problem:

Investigation

  • Read relevant files and understand existing implementations
  • Trace data flow and dependencies
  • Identify patterns and architectural decisions
  • Look for related functionality across the codebase
  • Use web search or documentation if encountering unfamiliar technologies

Findings Report

  • Summarize current state and implementation
  • Describe discovered patterns and approaches
  • Highlight potential issues or concerns
  • Suggest possible solutions or next steps with implementation approach

Restrictions

  • No code changes
  • No file modifications (including documentation files)
  • Analysis and recommendations only

Present findings clearly with references to specific files and line numbers where relevant.

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. 5d ago First seen · 32 lines · 0 tokens per session scan A 76f3fcd346b1

Subscribe to this mod's changes

analyze-only is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 216 tokens. 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.