LLM-driven self-improvement of the Vodou codebase — one small change at a time, fully tested, project-only, with backups. Can be scheduled to run continuously until stopped.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Vodou Self-Improve — Steward the Codebase to Release Quality
## Mission
You are improving the **Vodou project in this directory only**. Your job: make **one small, concrete improvement** per run, **run the full test gate** before moving on, and **never** leave this project directory or wipe major files. When done, schedule the next run so improvement continues until the user stops it.
---
## Guardrails (MANDATORY)
1. **Project directory only** — All edits, creates, deletes, and command execution (e.g. `cargo test`) MUST be confined to the Vodou project root (the directory containing `oi`, `vodou-core`, `Cargo.toml`, `.vodou/`). NEVER write, delete, or run commands that affect paths outside this project.
2. **No major file wipes** — Do NOT delete or overwrite in-place major files (e.g. `Cargo.toml`, `src/main.rs`, `README.md`, whole `src/` subdirs) without first creating a timestamped backup under `.vodou/backups/` (e.g. `.vodou/backups/2026-02-16_main.rs.bak`). When in doubt, backup first.
3. **One task per run** — Execute exactly one improvement from the plan (or one LLM-chosen task). Do not start the next task in the same run.
…
The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_eg4ois2ptr64x4gh
GET https://markdownregistry.com/api/v1/resolve?ref=vodouai/os/self-improve
GET https://markdownregistry.com/api/v1/blob/f7617443a74a8c300969e210b96c445fa532d33fd71d21da550f898bac278392
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
vodouai/os · integrations/claude-code-plugin/skills/vodou-memory/SKILL.md · Use the user's Vodou memory — recall what they told any AI before, and save what matters now. Use when the user…
vodouai/os · integrations/claude-code-plugin/skills/vodou-setup/SKILL.md · Install or connect the Vodou engine so this plugin's memory tools and hooks work. Use when the session-start hook…
vodouai/os · skills/agents/design/visual-storyteller/SKILL.md · Visual storytelling agent that structures presentations, plans data visualizations, builds case study narratives, and…
vodouai/os · skills/agents/engineering/ai-engineer/SKILL.md · Expert AI engineer for LLM integration, RAG pipelines, prompt engineering, model evaluation, and AI agent development
ginlix-ai/langalpha · plugins/langalpha_service/skills/self-improve/SKILL.md · Report issues and propose fixes to improve your own capabilities when you encounter errors or limitations
tobihagemann/turbo · codex/skills/self-improve/SKILL.md · Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the…
tobihagemann/turbo · claude/skills/self-improve/SKILL.md · Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the…
danmcinerney/orchflows · example-workflows/self-improve/skills/self-improve/SKILL.md · Review selected native agent history to improve the local environment, custom workflows, or Orchflows itself.
