By Yuvasee
Autonomous session orchestrator for multi-phase development workflows: manages code reviews, implementation, testing, and PR readiness across sessions with git worktree support, dual-agent AI comparisons, and structured phase-based plans.
Analyze changed code for quality issues: $ARGUMENTS
Create implementation plan: $ARGUMENTS
Create GitHub PR review comments from review findings: $ARGUMENTS
Deep-dive investigation on: $ARGUMENTS
Execute task: $ARGUMENTS
You are executing the [phase] phase of a Samocode session. Your goal is to [goal].
Session wrap-up and summary generation. Use after PR readiness passes.
Execute plan phases iteratively. Use during implementation phase to build features.
Initialize new Samocode sessions. Creates working directory, session folder, and _overview.md.
Deep-dive codebase exploration for investigation phase. Use at start of sessions to understand problem space.
Run Anthropic Claude CLI as a subagent for second opinions, code reviews, and questions. Use from a Codex (or other) session when you want Claude's perspective.
Run OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI model's perspective.
Create GitHub PR review comments from review findings. Use after running a code review to post findings as line-bound comments.
Execute implementation tasks with different approaches (single, dual-agent, plan-based).
Deep-dive investigation with documentation output.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Walk-away AI coding sessions, locally orchestrated. Drives Claude or Codex through full SDLC phases with human gates, so you can hand off multi-hour engineering work and walk away.
You give samocode a real engineering task — research a codebase, plan a refactor, implement a feature, run tests, clean up. It runs an AI CLI in a loop, walking your task through investigation → requirements → planning → implementation → testing → quality phases. It pauses to ask you questions when it needs to (_qa.md), waits for plan approval, and notifies you on Telegram when something needs your attention. You come back two hours later, your branch has the work done, with commits, tests, and a summary.
It's open-source, runs Claude or Codex as the orchestration provider (Gemini available as a second-opinion subagent), and runs locally — no SaaS, no proxy, your code never leaves your machine.
Not an engineer? See docs/eli10.md for a friendly walkthrough.
legacy/." (30 min unattended)If your task is "I need to think about this with the AI for 10 minutes" — use Claude / Cursor / Aider directly. samocode is for the cases where you'd rather walk away.
pip install samocode
Create .samocode in your project root:
MAIN_REPO=~/your-project
WORKTREES=~/your-project/worktrees/
SESSIONS=~/your-project/_sessions/
Run a session:
samocode \
--config ~/your-project/.samocode \
--session add-jwt-auth \
--task "Add JWT-based authentication to the Express API"
samocode creates a worktree, spawns the AI CLI, walks the task through phases, and signals when it's done or needs you. Watch progress in ~/your-project/_sessions/26-XX-XX-add-jwt-auth/_overview.md.
To hack on samocode itself, clone the repo instead:
git clone https://github.com/Yuvasee/samocode ~/samocode
cd ~/samocode && pip install -r requirements.txt && samocode install
samocode install links samocode skills into both ~/.claude/skills and ~/.codex/skills. Claude-only slash commands and agent files are linked into ~/.claude; Codex provider runs read the phase agent files directly from the installed samocode package. From a repo checkout it symlinks (so edits go live); from a pip install it auto-detects and copies — use --copy only to force copying from a checkout. samocode never clobbers real files or foreign symlinks you own.
Re-run behavior depends on mode: symlink installs are idempotent (re-running refreshes samocode's own links), while copy installs are placed once and skipped on re-run — to update a copy install, run samocode uninstall (or delete the copied files) and install again.
samocode uninstall removes only samocode-owned symlinks. Copy-mode installs are real files samocode cannot prove it created, so they are left in place and reported as skipped — delete them manually if needed.
After a pip install, run samocode install once to make the skills, agents, and commands available to your provider (it auto-copies from a packaged install).
Upgrading from the old
install.sh? Skills that were removed or renamed (e.g.adhd,gemini) leave dangling symlinks in~/.claude/skillsand~/.codex/skills. Remove them manually:rm ~/.claude/skills/adhd ~/.codex/skills/gemini(ignore "No such file" errors).
→ See examples/ for runnable scenarios.
samocode's skills (investigation, planning, implementation, quality, testing, and more) are plain Agent Skills — a SKILL.md per directory — so any compatible agent can use them without the orchestrator. Install them cross-agent in one line:
npx skills add Yuvasee/samocode
npx claudepluginhub yuvasee/samocodeDescribe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.
Harness engineering for Claude Code — hook-enforced dual review, state-machine gates, and fail-closed safety where it counts.
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
Claude Code settings and skills for spec-driven development workflows