vardoger

A cross-platform plugin for AI coding assistants (Cursor, Claude Code, OpenAI Codex, OpenClaw, GitHub Copilot CLI, Windsurf, Cline) that reads your conversation history, extracts behavioral patterns, and generates personalized system prompt additions — making the assistant progressively better suited to how you work.

All processing happens locally. No data ever leaves your machine.

Prerequisites

Python 3.11+

Platform	Command
macOS	brew install python@3.13 (install Homebrew) or python.org/downloads/macos
Debian / Ubuntu	sudo apt install python3
Fedora	sudo dnf install python3
Windows	winget install Python.Python.3.13 or python.org/downloads/windows

pipx

Recommended for installing vardoger as an isolated CLI tool. Full instructions at pipx.pypa.io/stable/installation.

Platform	Command
macOS	brew install pipx && pipx ensurepath
Debian / Ubuntu	sudo apt install pipx && pipx ensurepath
Fedora	sudo dnf install pipx && pipx ensurepath
Windows	scoop install pipx or pip install --user pipx && pipx ensurepath

Quick Start

pipx install vardoger
vardoger setup cursor        # or claude-code, codex, openclaw, copilot, windsurf, cline

Then tell your assistant: "Personalize my assistant."

Looking for the in-app plugin listings? Track review status for each marketplace (PyPI, Cursor, Claude Code, Codex, Copilot CLI, Windsurf, Cline, ClawHub) in MARKETPLACE_STATUS.md.

Previous pre-releases. pipx install vardoger now resolves to the stable 0.2.x line. The beta install paths below stay here for anyone still pinning an earlier release; new installs should not need them.

# opt into future pre-releases (0.2.0bN, etc.):
pipx install --pip-args="--pre" vardoger
# or pin an older pre-release:
pipx install vardoger==0.1.0b3
# or run without installing:
uvx vardoger --help

CLI Commands

Command	Purpose
vardoger setup <platform>	Register vardoger with a platform (cursor, claude-code, codex, openclaw, copilot, windsurf, cline).
vardoger status [--platform X] [--json]	Report whether each personalization is fresh or stale.
vardoger prepare --platform X [--batch N] [--synthesize]	Produce the batched prompts used by the AI-driven skill pipeline.
vardoger write --platform X	Read synthesized personalization from stdin and write it to the platform's rules file (supports YAML-frontmatter confidence metadata).
vardoger feedback accept|reject --platform X [--reason TEXT]	Record whether you kept or rejected the last generation. reject auto-reverts to the prior generation.
vardoger compare --platform X | --all [--window DAYS] [--json]	Compare heuristic conversation-quality metrics before vs. after the latest personalization.

How It Works

1. Read — Parses conversation history already stored on disk by each platform
2. Analyze — The host AI model identifies patterns in your communication style, tech stack, workflow, and preferences
3. Generate — Produces a system prompt addition tailored to you
4. Deliver — Writes the addition to the platform's native config (.cursor/rules/, .claude/rules/, AGENTS.md, etc.)

First run vs. incremental runs. By default vardoger does not apply a time window — the first run reads your full local history (that is when the signal is richest and a windowed default would silently drop older sessions you never get a second chance to feed in). After that, a per-conversation checkpoint store at ~/.vardoger/state.json ensures every subsequent run only reprocesses new or changed conversations, so refreshes stay fast. If you have very large local history and want to cap the first-run cost, pass --since DAYS (e.g. vardoger prepare --platform cursor --since 90); use --full to force a full re-crawl that bypasses the checkpoint.

Supported Platforms

Platform	History Source	Prompt Delivery	Integration
Cursor	Agent transcript JSONL	.cursor/rules/vardoger.md	MCP server
Claude Code	Session JSONL	.claude/rules/vardoger.md	Plugin with skill
OpenAI Codex	Session rollout JSONL	~/.codex/AGENTS.md	Plugin with skill
OpenClaw	Session JSONL	~/.openclaw/skills/vardoger-personalization/SKILL.md	Skill
GitHub Copilot CLI	~/.copilot/session-state/*.jsonl	~/.copilot/copilot-instructions.md (global) or <project>/.github/copilot-instructions.md (project) — managed inside a <!-- vardoger:start --> fenced section	CLI-only
Windsurf	~/.codeium/windsurf/**/*.jsonl	~/.codeium/windsurf/memories/global_rules.md (global, fenced section) or <project>/.windsurf/rules/vardoger.md (project, dedicated file)	CLI-only
Cline	VS Code globalStorage/.../tasks/*/api_conversation_history.json	<project>/.clinerules/vardoger.md if .clinerules is a directory, otherwise a fenced section in <project>/.clinerules (project-only)	CLI-only

Development

Requires uv (Python package manager):

git clone https://github.com/dstrupl/vardoger.git
cd vardoger
uv sync
.venv/bin/vardoger --help

Project Layout

src/vardoger/          # shared core — history reading, analysis, prompt generation
plugins/_shared/       # shared analysis/personalization skill authored once
plugins/cursor/        # Cursor MCP server config, install script
plugins/claude-code/   # Claude Code plugin manifest, skills
plugins/codex/         # Codex plugin manifest, skills
plugins/openclaw/      # OpenClaw skill
plugins/copilot/       # GitHub Copilot CLI plugin manifest, skills
plugins/windsurf/      # Windsurf install snippet and rules delivery
plugins/cline/         # Cline MCP-marketplace manifest + llms-install guide
tests/                 # all tests, mirroring src/ structure

• Platform-agnostic logic lives under src/vardoger/.
• Platform-specific integration (manifests, skills, install scripts) lives under plugins/<platform>/.
• Tests live in tests/, mirroring the source tree.

See AGENTS.md for full coding standards and quality checks.

Quality gates

CI enforces a combined quality bar on every push and pull request:

• ruff check / ruff format --check — lint (incl. complexity, pylint, return, pathlib, tryceratops rules) and formatting.
• mypy src/ — strict type checking.
• pytest --cov=vardoger --cov-fail-under=80 — tests across Python 3.11–3.13 with a combined 80% coverage floor.
• A parallel security job runs bandit -r src/ and pip-audit --skip-editable to catch common code smells and dependency CVEs.

Run the full bundle locally before pushing:

uv run ruff check . && uv run ruff format --check . && uv run mypy src/ && uv run pytest --cov=vardoger --cov-fail-under=80

Contributing

Contributions are welcome. Short version:

1. Fork dstrupl/vardoger on GitHub and clone your fork.
2. uv sync and create a topic branch.
3. Make your changes with tests and run the quality-gate one-liner above.
4. Push to your fork and open a PR against main.

CI (test on Python 3.11/3.12/3.13 plus a security job) will run automatically on the PR. First-time contributors may need a maintainer to click Approve and run before the first workflow execution.

See CONTRIBUTING.md for the full walkthrough and AGENTS.md for coding standards and commit-message conventions.

Releasing to PyPI

CI runs automatically on every push and PR (lint, type check, tests across Python 3.11–3.13). To publish a new version:

1. Bump version in pyproject.toml
2. Commit and push to main
3. Go to Releases > Create a new release
4. Create a new tag matching the version (e.g. v0.1.0), add a title and description
5. Click Publish release

The publish.yml workflow builds the package and uploads it to PyPI via trusted publishers (no API tokens needed). Once complete, pipx install vardoger will pull the new version.

Status

Public beta. The 0.3.x line is published on PyPI and actively maintained; marketplace listings are rolling out per MARKETPLACE_STATUS.md. See PRD.md for the full product requirements document.

Privacy and security

• PRIVACY.md — what vardoger reads, writes, and (importantly) does not send anywhere.
• SECURITY.md — how to report a vulnerability privately.

License

Licensed under the Apache License, Version 2.0.