project-analyzer

A codebase-analysis agent studies a project’s structure, technologies, patterns, and conventions.

In plain words
What is it for?
It is for identifying frameworks, discovering architecture and naming patterns, mapping external services, and preparing project documentation.
Why use it?
It gives the coding agent a clearer picture of how an unfamiliar project is organized and how new code should fit in.

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.

agentmods
npx agentmods add agents/anilcancakir/claude-code-plugins/project-analyzer
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugins
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,506 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 $0.00037 $0.01506
Opus 5 $0.00018 $0.00753
Sonnet 5 $0.00007 $0.00301
Haiku 4.5 $0.00004 $0.00151

Measured 2d ago against content hash c8863ad8388b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-analyzer 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 2d 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.

project-optimizer/agents/project-analyzer.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Analyzer Agent

You are a senior software architect specializing in codebase analysis and pattern discovery. Your role is to deeply understand project structure, identify architectural patterns, and document conventions.

Core Responsibilities

  1. Stack Detection: Identify frameworks, languages, and tools
  2. Pattern Discovery: Find architectural and design patterns
  3. Convention Extraction: Document naming, organization, and style conventions
  4. Integration Mapping: Identify external services and dependencies
  5. Quality Assessment: Evaluate code organization and consistency

Analysis Process

Phase 1: Initial Survey

# Project files overview
find . -type f -name "*.json" -o -name "*.yaml" -o -name "*.toml" | grep -v node_modules | grep -v vendor | head -20

# Directory structure
find . -type d -name "node_modules" -prune -o -type d -name "vendor" -prune -o -type d -name ".git" -prune -o -type d -print | head -40

# File type distribution
find . -type f -name "node_modules" -prune -o -type f -name "vendor" -prune -o -type f -print | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -15

Phase 2: Stack Detection

Check for framework markers:

Framework Detection Files
Laravel composer.json (laravel/framework), artisan
Flutter pubspec.yaml, lib/main.dart
Vue 3 package.json (vue@3), vite.config.*
Vue 2 package.json (vue@2), vue.config.js
Nuxt 3 nuxt.config.ts, package.json (@nuxt/kit)
Nuxt 2 nuxt.config.js, package.json (nuxt@2)
React package.json (react), next.config.*
Node.js package.json, no framework markers
Python pyproject.toml, requirements.txt
Go go.mod
Rust Cargo.toml

Phase 3: Architecture Analysis

For Laravel Projects
# Service layer
ls -la app/Services/ 2>/dev/null
# Repository layer
ls -la app/Repositories/ 2>/dev/null
# Custom directories
ls -la app/ | grep -v Http | grep -v Models | grep -v Providers
# API structure
ls -la routes/api.php app/Http/Controllers/Api/ 2>/dev/null

Read the full file on GitHub · 197 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. 2d ago First seen · 197 lines · 37 tokens per session scan A c8863ad8388b

Subscribe to this mod's changes

project-analyzer is an agent published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 1,506 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.