Enforces atomic commit workflows and surgical code changes with AST-based refactoring, structured planning, automated code review, CI/CD pipelines, memory management, and documentation generation for precise, verifiable software development.
Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.
Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.
Surface in-task AI collaboration protocols one tactic at a time. Use when the user refers to entities by colloquial labels, asks how to structure a Claude workflow, or describes a multi-step workflow without durable URLs.
Guide stable API and interface design. Use when creating REST or GraphQL endpoints, defining type contracts, or establishing frontend/backend or module boundaries.
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via `/askme`.
ODIN's AxiomMode register -- formal-logic English with predicate-form claims, Hoare-triple framing, and ASCII shortened-English keywords. CompactAxiomEnglish register subsumed. Daily-driver register for coding work.
Communication style for non-technical builders — product managers, founders, designers, and no-code/low-code users who build things without deep programming expertise. Leads with outcomes, uses plain language, maintains honesty without jargon overload.
Outline Driven Development(ODIN)'s approach to Claude output style; Precise and effective
Output style for the duet working posture (user as director, agent as executor). Minimizes cognitive load between picks: decisions before prose, structural/taste framing first, jargon on demand, batched questions with concrete previews, short execution updates, no validation language, no recap. Goal — eliminate the review bottleneck and prevent codebase-understanding debt by distributing review across the task at pick-time.
Linus Torvalds. Special-case elimination is good taste. Complexity discipline is law. Blunt about the work; be harsh.
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 claimnpx claudepluginhub outlinedriven/odin-claude-plugin --plugin odinBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
Outline-Driven Development (nicknamed ODIN) — Advanced code agent system for Claude Code with surgical precision, diagram-first engineering, and comprehensive workflow automation.
Methodology: outline-driven-development · Codex CLI: odin-codex-plugin · Gemini CLI: odin-gemini-cli-extension · Site: outlinedriven.github.io
ODIN is a professional-grade Claude Code plugin that transforms Claude into a sophisticated code agent with comprehensive workflow automation and rigorous engineering methodology.
Key Capabilities:
wget -O ~/.claude/CLAUDE.md https://raw.githubusercontent.com/OutlineDriven/odin-claude-plugin/refs/heads/main/CLAUDE.md && claude plugin marketplace add OutlineDriven/odin-claude-plugin && claude plugin install odin@odin-marketplace
# List available agents
/agents
# View all commands
/help
# See the installed plugins
/plugin
ODIN follows strict engineering principles:
Before any non-trivial implementation:
Skills are invokable workflows that extend ODIN with process- and domain-specific protocols. Invoke with /<skill-name>; many also trigger on natural language cues described in their frontmatter.
askme - Verbalized Sampling protocol for deep intent exploration before planningbatch-ask-me - Walk a dependency-aware design tree in batched question rounds until shared understandingmutual-sync - Three-way grounding: verify user, agent, and codebase share one picture of current state before proceedingloop-me - Design recurring workflows through a stateful askme session and cwd specsto-questionnaire - Turn a knowledge gap into an async questionnaire for the person who can answer itplan - Thorough read-only planning before any actioncontexts - Coordinate context sweep before codinginit - Analyze a codebase and create or improve AGENTS.mdbrainstorm - Explore vague or ambitious ideas into a right-sized requirements-only planexplore - Read-only codebase exploration to map structure, symbols, and dependencieszoom-out - Step up one layer of abstraction to map surrounding modules and invariantsstrategy - Sharp interview to write or maintain STRATEGY.md as the product anchorideate - Generate grounded, divergent ideas from the codebase into docs/ideationdesign - Set visual and interaction direction for UI surfaces before writing codepov - Decisive, project-grounded verdict on adopting or switching technologyresearch - Gather external knowledge from authoritative sources with verified citationsteach - Run a persistent cwd teaching workspace across missions, lessons, resources, and learning recordswriting-fragments - Mine heterogeneous raw material into an append-only pile before shapingwriting-shape - Shape a raw pile into an article paragraph by paragraph with argued formatswriting-beats - Build a grounded article journey one candidate beat at a timeCodex CLI reflector — independent critic, oracle, and metacognition layer
Auto-block AI-driven edits when cognitive complexity or helper sprawl exceed configured budgets. Rust pilot in V1.
A senior multi-agent engineering workflow plugin for Claude Code, Codex, and GitHub Copilot CLI.
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Codebase exploration, refactoring, and quality analysis
Skills and agents for diagrams, codebase patterns, hypothesis testing, Socratic thinking, file querying, frontend design, image generation, and command creation
Project discovery, planning, and quality analysis system with parallel agents
Focused agentic engineering workflow: design-doc, spec, plan, implement, tdd, refactor, review, address-pr-feedback, browser-verify, explain-visually, compress, branch, and commit.