analyze

A command that reviews a project or selected code for quality, security, performance, architecture, and technical debt, then gives prioritized recommendations.

In plain words
What is it for?
Use it for whole-project audits, security checks, performance investigations, architecture reviews, or focused quality checks at different depths.
Why use it?
It provides a structured assessment before a release or refactor and helps locate risks or slow areas.

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/drag88/claude-dev-framework/analyze
Clone the repo
git clone --depth 1 https://github.com/drag88/claude-dev-framework
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 703 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 $0.00014 $0.00703
Opus 5 $0.00007 $0.00351
Sonnet 5 $0.00003 $0.00141
Haiku 4.5 $0.00001 $0.00070

Measured yesterday against content hash 5f1f426e80eb, 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 yesterday.

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/analyze.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cdf:analyze - Code Analysis and Quality Assessment

Multi-domain code analysis with systematic assessment and prioritized recommendations.

Quick Start

# Analyze entire project
/cdf:analyze

# Security-focused analysis
/cdf:analyze src/auth --focus security

# Deep performance analysis
/cdf:analyze --focus performance --depth deep

# Quick quality check
/cdf:analyze src/components --focus quality --depth quick

When to Use

Use /cdf:analyze when:

  • Assessing code quality before a release or refactor
  • Scanning for security vulnerabilities in sensitive components
  • Identifying performance bottlenecks in slow areas
  • Reviewing architecture and technical debt

Don't use this command for: Making code changes (use /cdf:improve), troubleshooting specific bugs (use /cdf:troubleshoot).

Diff and PR review belong to the compound-engineering:ce-code-review host skill; /cdf:analyze remains the whole-repo audit tool.

Triggers

  • Code quality assessment requests for projects or specific components
  • Security vulnerability scanning and compliance validation needs
  • Performance bottleneck identification and optimization planning
  • Architecture review and technical debt assessment requirements

Usage

/cdf:analyze [target] [--focus quality|security|performance|architecture] [--depth quick|deep] [--format text|json|report]

Behavioral Flow

  1. Discover: Categorize source files using language detection and project analysis
  2. Scan: Apply domain-specific analysis techniques and pattern matching
  3. Evaluate: Generate prioritized findings with severity ratings and impact assessment
  4. Recommend: Create actionable recommendations with implementation guidance
  5. Report: Present comprehensive analysis with metrics and improvement roadmap

Key behaviors:

  • Multi-domain analysis combining static analysis and heuristic evaluation
  • Intelligent file discovery and language-specific pattern recognition
  • Severity-based prioritization of findings and recommendations
  • Comprehensive reporting with metrics, trends, and actionable insights

Read the full file on GitHub · 92 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. yesterday First seen · 92 lines · 14 tokens per session scan A 5f1f426e80eb

Subscribe to this mod's changes

analyze is a command published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 703 once invoked, about $0.0001 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.