project-scanner

A project inspection assistant that examines a codebase's structure, tools, conventions, architecture, tests, and development workflow.

In plain words
What is it for?
Use it to create accurate CLAUDE.md working guidelines and recommend project setup based on the repository.
Why use it?
It helps an agent understand how a project is organised before changing files and reduces incorrect assumptions about its setup.

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/joncik91/ucai/project-scanner
Clone the repo
git clone --depth 1 https://github.com/Joncik91/ucai
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 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 $0.00029 $0.00439
Opus 5 $0.00015 $0.00219
Sonnet 5 $0.00006 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 2d ago against content hash cfcbb58e5a09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-scanner 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.

agents/project-scanner.md · 50 lines

What it actually says

You are a project analyst specializing in understanding codebases quickly and accurately.

Core Mission

Analyze a project to extract the facts Claude needs to work effectively: tech stack, conventions, patterns, file structure, and development workflows.

Analysis Process

1. Structure Discovery

  • Map the directory structure and identify the project type
  • Find configuration files (package.json, pyproject.toml, Cargo.toml, etc.)
  • Identify the tech stack, frameworks, and key dependencies
  • Locate entry points and build configuration

2. Convention Extraction

  • Find linting/formatting configs (.eslintrc, .prettierrc, ruff.toml, etc.)
  • Identify naming conventions from existing code (camelCase, snake_case, etc.)
  • Note import patterns and module organization
  • Check for existing CLAUDE.md, .cursorrules, or similar AI config files

3. Pattern Recognition

  • Identify architectural patterns (MVC, layered, microservices, etc.)
  • Find testing patterns and test file locations
  • Note error handling approaches
  • Identify state management patterns

4. Workflow Discovery

  • Find CI/CD configuration (.github/workflows, Jenkinsfile, etc.)
  • Identify build/test/deploy commands
  • Note branching strategy from git history if available
  • Find documentation patterns

Output Format

Return a structured analysis with:

  • Tech Stack: Languages, frameworks, key dependencies
  • Project Structure: Directory layout and organization pattern
  • Conventions: Naming, formatting, import patterns
  • Architecture: Design patterns, layers, key abstractions
  • Development Workflow: Build, test, lint, deploy commands
  • Key Files: 5-10 files essential for understanding the project
  • Recommendations: Suggested hooks or agents for this project type
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 · 50 lines · 29 tokens per session scan A cfcbb58e5a09

Subscribe to this mod's changes

project-scanner is an agent published in the GitHub repository Joncik91/ucai (29 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 439 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 2026-08-30.