Skip to main content

Workspace summary generator for AI-assisted development workflows.

Project description

IntelScan

IntelScan is a lightweight workspace-summary tool for AI-assisted development workflows.

It scans the repository, generates a structured manifest, and writes a human-readable memory file so agents can understand the repo without rescanning everything from scratch.

What it generates

  • workspace.json - machine-readable workspace metadata
  • workspacememory.md - human-readable workspace summary

The generated outputs also include an inferred project structure section so agents can quickly see the repo layout, entry points, and major components.

These files are generated at the project root and are ignored by git.

Installation

Prerequisites:

  • Python 3.8+
  • Git on PATH if they want Git metadata included in the generated summary

Install from the repository:

git clone https://github.com/Debanshu2005/IntelScan
cd IntelScan
python -m pip install .

After the first PyPI release, users will also be able to install it directly with:

pip install intelscan

After installation, the CLI commands are available:

intelscan --root .
intelscan-agent --root . --agent-cmd "python your_agent_task.py"

Create an agent guide in a project:

intelscan --root . --init-agents

For local development without installing globally:

python workspace_scanner.py --root .
python agent_coordinator.py --root . --agent-cmd "python your_agent_task.py"

The repository now uses a src/intelscan/ package layout. The two root-level Python files are thin development launchers so the source-tree commands above still work.

Main files

  • src/intelscan/workspace_scanner.py - scans the repo and generates the summary files
  • src/intelscan/agent_coordinator.py - wraps an agent command and refreshes the workspace files before and after the run
  • workspace_scanner.py - thin source-tree launcher for local development
  • agent_coordinator.py - thin source-tree launcher for local development
  • WORKSPACE_SCANNER.md - focused usage notes for the scanner
  • .vscode/tasks.json - editor tasks for manual scan and watch flows

Usage

Run a one-time scan:

intelscan --root .

Create AGENTS.md if the project does not already have one:

intelscan --root . --init-agents

Run in watch mode:

intelscan --root . --watch

Run through the coordinator:

intelscan-agent --root . --agent-cmd "python your_agent_task.py"

VS Code tasks

If you use VS Code, run these from Terminal -> Run Task:

  • Scan Workspace Once
  • Watch Workspace

Notes

  • The scanner ignores symlinks and keeps output writes inside the workspace root.
  • Git metadata is included when available, with safe non-interactive Git calls.

Publishing

Release notes for PyPI are in RELEASING.md. The repo also includes a GitHub Actions workflow for PyPI Trusted Publishing at .github/workflows/publish.yml.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

intelscan-0.1.0.tar.gz (16.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

intelscan-0.1.0-py3-none-any.whl (15.1 kB view details)

Uploaded Python 3

File details

Details for the file intelscan-0.1.0.tar.gz.

File metadata

  • Download URL: intelscan-0.1.0.tar.gz
  • Upload date:
  • Size: 16.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for intelscan-0.1.0.tar.gz
Algorithm Hash digest
SHA256 3ec82347c59be8719d1592dfa8509e6648ddf51dd4add1a3cb40239503bbb86f
MD5 bbaea9fbf30f498bc62f70fac07709c5
BLAKE2b-256 c3a24739031896b5dfcc6c3729a5180c8f57c468544df6d82963a02205ade006

See more details on using hashes here.

File details

Details for the file intelscan-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: intelscan-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 15.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.1

File hashes

Hashes for intelscan-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6e6c7e1de9af02789967b4dd6dcbdb76d384bf1e7686e6fc04b3d57c0cd54959
MD5 3122d5bcaf2a0672daa616f792295230
BLAKE2b-256 a076bb086f858994189f626ff015490fd1e3f8f815d22a377195549c39d9bb72

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page