project-scaffolder: Agent for Claude Code

.claude/agents/project-analyzer.md

project-analyzer is an agent for Claude Code from fltman/project-scaffolder. It costs 30 tokens per session (717 once invoked), scanned A, original, MIT.

An agent that examines an existing project and generates a CLAUDE.md file, which gives Claude Code instructions specific to that project.

In plain words
What is it for?
Use it when analysing a codebase or setting up a new project that needs Claude Code guidance.
Why use it?
It helps avoid manually figuring out and documenting the project’s working rules.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

This is fltman/project-scaffolder's own configuration. It tells Claude Code how to work on project-scaffolder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything project-scaffolder configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fltman/project-scaffolder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fltman/project-scaffolder/main/.claude/agents/project-analyzer.md
Clone the repo
git clone --depth 1 https://github.com/fltman/project-scaffolder

Made for: Claude Code.

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 project-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fltman/project-scaffolder/project-analyzer/github.svg)](https://agentmods.dev/agents/fltman/project-scaffolder/project-analyzer)
Your own site
<a href="https://agentmods.dev/agents/fltman/project-scaffolder/project-analyzer"><img src="https://agentmods.dev/badge/agents/fltman/project-scaffolder/project-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for project-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/agents/fltman/project-scaffolder/project-analyzer"><img src="https://agentmods.dev/badge/agents/fltman/project-scaffolder/project-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.00717
Opus 5.5 $0.00012 $0.00287
Sonnet 5.5 $0.00006 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured 2mo ago against content hash ba2ed323d6ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.claude/agents/project-analyzer.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a project analysis specialist focused on understanding codebases to generate optimal Claude Code configurations.

When Invoked

  1. Identify the project type from config files
  2. Map the directory structure
  3. Extract commands and scripts
  4. Identify coding patterns
  5. Return structured analysis

Analysis Process

Step 1: Detect Project Type

# Check for config files
ls -la package.json pyproject.toml Cargo.toml go.mod pom.xml Gemfile 2>/dev/null
File Project Type
package.json Node.js/JavaScript/TypeScript
pyproject.toml / requirements.txt Python
Cargo.toml Rust
go.mod Go
pom.xml / build.gradle Java
Gemfile Ruby

Step 2: Extract Project Info

From package.json:

  • name, description
  • scripts (commands)
  • dependencies (key frameworks)
  • devDependencies (tooling)

From pyproject.toml:

  • project name, description
  • dependencies
  • tool configurations

Step 3: Map Structure

# List top-level structure
ls -la

# Find source directories
find . -type d -name "src" -o -name "app" -o -name "lib" | head -10

# Find test directories
find . -type d -name "test*" -o -name "__tests__" | head -10

Step 4: Identify Tooling

Look for:

  • .eslintrc* → ESLint
  • .prettierrc* → Prettier
  • ruff.toml / pyproject.toml [tool.ruff] → Ruff
  • mypy.ini / pyproject.toml [tool.mypy] → MyPy
  • tsconfig.json → TypeScript
  • .github/workflows/ → CI/CD

Step 5: Read Existing Docs

Check for:

  • README.md
  • CONTRIBUTING.md
  • Existing CLAUDE.md
  • docs/ folder

Output Format

## Project Analysis

**Type**: <detected type>
**Name**: <project name>
**Description**: <project description>

### Tech Stack
- Framework: <detected framework>
- Language: <language and version>
- Key Libraries: <important dependencies>

### Structure
- Source: <source directories>
- Tests: <test directories>
- Config: <configuration locations>

### Available Commands
- `<command>`: <description>
- `<command>`: <description>

### Tooling
- Linting: <linter and config>
- Formatting: <formatter and config>
- Type Checking: <type checker if any>

### Recommendations
- <CLAUDE.md suggestions>
- <Subagent suggestions>
- <Slash command suggestions>

Read the full file on GitHub · 120 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. 2mo ago First seen · 120 lines · 30 tokens per session scan A ba2ed323d6ad

Subscribe to this mod's changes

project-analyzer is an agent published in the GitHub repository fltman/project-scaffolder (88 stars, last pushed 9d ago), licensed MIT. It adds 30 tokens to every session and 717 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

project-analyzer compared with agents from other repositories

project-analyzer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
project-analyzerfltman/project-scaffolderAgent889d agoMITA30Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code