analyze-project

A command that scans an existing codebase and documents its architecture, technologies, and project structure.

In plain words
What is it for?
Use it to detect frameworks, databases, deployment files, continuous-integration setup, and AI-related code, then create PROJECTANALYSIS.md and CLAUDE.md.
Why use it?
It gives developers a shared map of an unfamiliar project before they plan changes or analyze missing functionality.

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/alphaaiservice/cortex/analyze-project
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,974 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 $0.00043 $0.02974
Opus 5 $0.00022 $0.01487
Sonnet 5 $0.00009 $0.00595
Haiku 4.5 $0.00004 $0.00297

Measured yesterday against content hash 52c053a797cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-project 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-project.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Analyzer — Existing Codebase Intelligence

Analyze the existing project at: $ARGUMENTS (default: current directory)

This command scans an existing codebase and produces a comprehensive analysis that powers /gap-analysis, /retrofit, and /auto-build --existing.


Step 1: Discover Project Root & Type

# Detect project type from files present
ls -la $ARGUMENTS 2>/dev/null || ls -la .

Identify:

  • Backend framework: Look for requirements.txt, pyproject.toml, package.json, go.mod, Cargo.toml, pom.xml
  • Frontend framework: Look for next.config.*, nuxt.config.*, angular.json, vite.config.*, app.config.ts
  • Mobile framework: Look for app.json, app.config.ts (Expo), Podfile (iOS), build.gradle (Android)
  • Database: Look for alembic/, migrations/, prisma/, docker-compose.yml (DB services)
  • CI/CD: Look for .github/workflows/, .gitlab-ci.yml, Jenkinsfile, Dockerfile
  • AI/ML: Look for app/ai/, agents/, prompts/, model configs

Step 2: Deep Scan Architecture (Use Agent subagents (mode = "bypassPermissions") in parallel)

Scan 2A: Backend Analysis

Use Glob + Grep to find:
- Framework: FastAPI/Flask/Django/Express/NestJS/Spring/Go
- Auth: JWT, OAuth, session-based, Firebase Auth, Auth0, Clerk
- Token storage: HTTP-only cookies vs localStorage vs sessionStorage
- Database: MySQL/PostgreSQL/SQLite/MongoDB/Redis connections
- ORM: SQLAlchemy/Prisma/TypeORM/Mongoose/PyMongo/Beanie/Motor
- Payment: Stripe/Razorpay/PayPal integrations
- Email: SMTP/SendGrid/SES/fastapi-mail
- Task queue: Celery/Bull/RabbitMQ
- File storage: S3/GCS/local filesystem
- Search: Elasticsearch/Meilisearch/Algolia
- Real-time: WebSocket/Socket.IO/SSE/polling
- Cache: Redis/Memcached/in-memory

Scan 2B: Frontend Analysis

Use Glob + Grep to find:
- Framework: Next.js/React/Vue/Angular/Svelte
- UI library: shadcn/Ant Design/MUI/Chakra/Mantine/Bootstrap/Tailwind
- State management: Redux/Zustand/MobX/Recoil/Context
- Forms: React Hook Form/Formik/custom
- API client: Axios/fetch/TanStack Query/SWR
- Auth handling: Where tokens are stored, how auth state is managed
- Theme: Dark mode support? CSS variables? Tailwind dark?
- i18n: Any translation system?
- PWA: Service worker? Manifest?

Read the full file on GitHub · 324 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 · 324 lines · 43 tokens per session scan A 52c053a797cc

Subscribe to this mod's changes

analyze-project is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 43 tokens to every session and 2,974 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.