Odin Claude Plugin plugin for Grok Build
Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.
How to install Odin Claude Plugin in Grok Build
1. Add this repo as a plugin marketplace in Grok Build (once per computer):
grok plugin marketplace add OutlineDriven/odin-claude-plugin2. Install the plugin:
grok plugin install odin-core@OutlineDriven/odin-claude-plugin --trustReview before you trust it. --trust lets this plugin's hooks, MCP servers and scripts run code on your computer. It's a community repo that neither xAI nor GrokStacks has reviewed, so read its code first.
This repo's marketplace has 28 plugins; we checked odin-core, odin-critique, odin-planning. Install another the same way: grok plugin install <name>@OutlineDriven/odin-claude-plugin --trust (names under 'What it contains'). Then start a new Grok session, or press r in /plugins, to load it.
Inside Grok Build: type /plugins, open the Marketplace tab, press a and add OutlineDriven/odin-claude-plugin, then select odin-core and press i.
Command format: Grok Build's plugin guide
Runs a local MCP server (with npx, uvx or similar), so that tool needs to be installed, for example Node.js for npx.
What we checked: on Oct 18, 2026 it installed with grok 1.0.62 and Grok found 54 skills. That's an install check only: we haven't run it in a live Grok session.
What it contains
Skills (40)
ai-collab-protocols— Use when the user describes an AI workflow gap or uses an ambiguous cross-session reference such as 'the PR Bob mentioned'. Not for tasks that require source or remote-system changes.axiom-mode— Use when the user requests axiom, axiom-mode, axiom-compact, formal-logic, or compact form. Not for changing code or remote state.enforce-workflow-constraints— Use when any bounded workflow starts or reaches an action, path, proposal, or merge boundary. Refuses rather than default-allow on an unreadable constraint set.necessary-work— Use when work is about to grow past the ask, the task may already be done, or the user requests only the minimum. Not for executing the work: use tdd to build or strike-the-root to fix.post-change-check-gate— Use when an artifact or skill has just changed and is about to be called done, committed, or handed off. Not for remote, credential, publish, deploy, or irreversible changes.skill-gap-finder— Use when the user suspects no installed skill covers a task and wants proof. Names the owning skill or writes a missing-skill brief. Never routes or invokes the matched skill.verification-before-completion— Use when a task, feature, or fix is called done, complete, finished, or fixed, or before a commit, PR, or next task. Not for fact-checking: use verify-both-ways. Not for measuring: use verify-this.abstract-well— Use when the user wants to classify abstractions as useful, bad, or busy and keep one shallow level. Not for tasks requiring source or remote-system changes.askme— Use when eliciting intent/scope/referents or gating long/bundled/high-stakes/hard-to-undo work: exhaustive/collaborative/adversarial/gate/batch/interview/scan/proposal. Not for one fork: use decide.autoplan— Use when the user runs /autoplan on a plan or idea. Reviews, amends, and derives task IDs with a final human approval gate. Not for remote, credential, publish, deploy, or irreversible changes.backlog— Use when asked to park an undecided idea without representing it as decided or active work. Not for decided or active work: use the project task system.brainstorm— Use when the user begins knowledge work with notes, a transcript, or a brain dump, asks for divergent ideas (mode: ideate), or wants options shown in a local browser (mode: visual).converge— Use when the user wants to collapse an open decision field to one decision and record its rationale locally. Not for multi-lens pressure testing. No remote or irreversible changes.decide— Use when the user has a fork and wants it resolved and applied, not explored: "decide this", "choose the path", or "decide and fix it".define-goalstate— Use when the user wants the finished-system contract for a piece of work: behavior, protocols, allowed, forbidden, and impossible states with a state-space proof. Not for runtime verification.diverge— Use when the user wants to expand a decision field with additional options and dimensions. Not for selecting or applying an option: use decide. No source or remote-system changes.entropy-assisted-planning— Use when the user explicitly requests a Tarot draw or casually delegates an ambiguous choice among multiple valid approaches.fail-design— Use when a user wants to define failure states, recovery actions, bypasses, and degraded modes for a component during design. Not for runtime recovery.from-first-principle— Use when a user wants to rebuild a design, organization, or API from primitives. Not for a perspective take: use from-perspective.generalize— Use when asked to derive the general rule a request carries as examples instead of a stated rule, then bound it. Not for ambiguity in a stated request: use askme. Read-only.goal-init— Use when a durable effort needs an approved, checkable success predicate before work starts. Not for requirement-to-evidence ledgers. Never remote, credential, publish, deploy, or irreversible.graph-backbone— Use when defining, revising, or gate-replanning the project structural backbone in project-root graph.yaml. Not for remote, credential, publish, deploy, or irreversible changes.idea-sparkbox— Use when the user asks to park ideas or inspiration for later. Not for code, backlog, or divergence-class cards, or remote, credential, publish, deploy, or irreversible changes.leave-only-first-principle— Use when asked to prune a design or codebase until only primitives remain, producing a first-principles map. Not for remote, credential, publish, deploy, or irreversible changes.loop-me— Use when the user says "loop me" or asks to design a recurring workflow. Don't use for remote, credential, publish, deploy, or irreversible changes.minimap— Use when the user needs a compact read-only current-work view from Git state, recorded test evidence, and optional graph.yaml. Not for tasks that need source or remote-system changes.next-best-action— Use when a project is between phases, the author asks what to do next, too many threads are open, or work needs re-entry. Not for gating whether one named task may proceed.plan— Use when a user commits to a direction and asks to plan, brief, research, or operationalize it; or wants to enumerate designs, configurations, scenarios, and paths, audit a supplied plan, tune the review flow, or a plan-mode enforcement hoopossible-worlds— Use when a design dispute has at least two live interpretations and the caller wants worlds made explicit or a plain-language recommendation. Not for selecting a design or source/remote changes.pov— Use when asked to judge whether to adopt, switch, reject, or revisit technology, library, pattern, or architecture, or a second opinion. Not for scoping: use brainstorm. Not for forks: use decide.readiness-assessment— Use when a user asks for a gut-check on a decision or action, or asks whether enough is known to proceed. Not for numeric confidence scoring.show-way— Use when the user asks for a flattened view of roadmaps and next actions. Not for multi-session route planning: use wayfinder.attack-shape— Use when the user wants adversarial stress-testing of a proposed architecture, structure, or shape. Not for tasks that require source or remote-system changes.council— Use when the user asks for a council, second opinions, or parallel investigation. Not for cross-examination of existing proposals: use cross-critique.cross-critique— Use when independent proposals on a contested decision need cross-critique before choosing, reusing the original authors. Not for parallel multi-stance investigation: use council.cross-lens-converge— Use when one reviewer is not enough because failure modes are heterogeneous, or a claim needs cross-lens pressure before it ships. Not for collapsing a decision field: use converge.decision-rationale-gaps— Use when a current decision needs pressure-testing until the rationale is clear to a skeptic. Not for tasks requiring source or remote-system changes.doubt-driven— Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.from-perspective— Use when an answer is wanted from one named seat only: breaking, business, career, codebase, human, impact, innovation, moat, rent-seeking, skeptic, or stability. Not for multi-lens synthesis: use prism. Not for rebuilding from primitives:load-bearing-assumption-test— Use when the user asks why a plan is wrong or says "poke holes in this". Not for tasks that require source or remote-system changes.
MCP servers (4)
sequential— stdio servercritic— stdio servershannon— stdio serverrepomix— stdio server
Plugins in this marketplace (28)
odin-core— Core ODIN gates every session runs: intent, scope, verification, and hand-off checks.odin-planning— ODIN workflows for shaping intent into approved plans, specs, and task lists.odin-critique— ODIN workflows for pressure-testing a decision from independent seats and lenses.odin-product— ODIN workflows for product strategy, market signals, and developer adoption.odin-code— ODIN workflows for writing, changing, and simplifying code.odin-review— ODIN workflows for reviewing diffs, branches, and implementations against their specs.odin-testing— ODIN workflows for tests, properties, mutation, and behavioral verification.odin-git— ODIN workflows for commits, branches, pull requests, review feedback, and issue tracking.odin-release— ODIN workflows for cutting, gating, publishing, and announcing releases.odin-run— ODIN workflows for executing plans, orchestrating subagents, and bounded autonomous loops.odin-infra— ODIN workflows for CI, deployment, observability, cost, and infrastructure tooling.odin-security— ODIN workflows for security review, vulnerability triage, and defensive implementation.odin-fuzzing— ODIN workflows for fuzz harnesses, fuzzer setup, sanitizers, and coverage analysis.odin-research— ODIN workflows for source-backed investigation, verification, and design rationale.odin-knowledge— ODIN workflows for memory, session continuity, decision records, and retrospectives.odin-learn— ODIN workflows for teaching, explaining, drilling, and onboarding.odin-people— ODIN workflows for team dynamics, culture profiles, and negotiation.odin-agent— ODIN workflows for configuring agent harnesses, MCP servers, and repository agent surfaces.odin-skills— ODIN workflows for authoring, auditing, benchmarking, and publishing agent skills.odin-writing— ODIN workflows for documentation, editorial prose, and copy.odin-visual— ODIN workflows for diagrams, decks, canvases, and visual explainers.odin-design— ODIN workflows for interface design, prototypes, and visual fidelity.odin-web— ODIN workflows for browser testing, web performance, SEO, and extensions.odin-typescript— ODIN workflows for modern TypeScript development.odin-python— ODIN workflows for modern Python development.odin-native— ODIN workflows for native systems, toolchains, and performance.odin-apple— ODIN workflows for software on Apple platforms.odin-formal— ODIN workflows for formal methods: model checking, SMT solving, deductive verification, and proof assistants.
About this listing
Odin Claude Plugin is a community plugin on GitHub by OutlineDriven, built for Grok Build. We install-checked it in Grok; we haven't run it in a live session or reviewed its code. When we installed it, Grok found 40 skills, 4 MCP servers, 28 plugins in this marketplaces. Its license is Apache-2.0. We checked commit 8ce0e87a3e88. It's one of 143 listings in the Design category on GrokStacks.
Stacks Weekly: every new Grok Build and Codex plugin, every Tuesday.
One short email for GrokStacks and CodexStacks readers, with each new plugin's install line and what it ships. Subscribe and get the free starter list: 20 Grok Build plugins worth installing first.
You'll get a confirmation email first. Unsubscribe anytime.
Odin Claude Plugin FAQ
How do I install Odin Claude Plugin in Grok Build?
Add the repo as a marketplace with grok plugin marketplace add OutlineDriven/odin-claude-plugin, then run grok plugin install odin-core@OutlineDriven/odin-claude-plugin --trust. This repo's marketplace has 28 plugins; we checked odin-core, odin-critique, odin-planning. Install another the same way: grok plugin install <name>@OutlineDriven/odin-claude-plugin --trust (names under 'What it contains'). Then start a new Grok session, or press r in /plugins, to load it.
Is Odin Claude Plugin an official Grok Build plugin?
No. Odin Claude Plugin is a community plugin on GitHub by OutlineDriven, not in xAI's official Grok Build marketplace. We checked that it installs and what Grok loads from it, but haven't run it in a live Grok session or reviewed its code.
What does Odin Claude Plugin include?
According to what Grok loaded in our install check, Odin Claude Plugin includes 40 skills, 4 MCP servers, 28 plugins in this marketplaces: ai-collab-protocols, axiom-mode, enforce-workflow-constraints, necessary-work, post-change-check-gate, skill-gap-finder….
Details
- Type
- Plugin
- Category
- Design
- Source
- Community plugin, built for Grok Build
- License
- Apache-2.0
- Author
- OutlineDriven
- Keywords
- agentic-coding, ai-coding-agent, claude-code, claude-code-plugin, claude-code-plugins, claude-code-skill, claude-code-skills, claude-marketplace, claude-plugins, claude-skills, cli-tools, coding-paradigm
- Source repo
- https://github.com/OutlineDriven/odin-claude-plugin
- Checked commit
8ce0e87a3e88- Homepage
- https://outlinedriven.github.io
- Checked by GrokStacks
- Install-checked in Grok Build on Oct 18, 2026; not run in a live session
Something wrong or missing? Submit or improve this listing. Marketplace listings also refresh automatically every night.
For maintainers: badge and embeds
Maintain Odin Claude Plugin? Add the badge; it links to this page.
Markdown
[](https://grokstacks.com/p/odin-claude-plugin/)HTML
<a href="https://grokstacks.com/p/odin-claude-plugin/"><img src="https://grokstacks.com/badge.svg" alt="Listed on GrokStacks" width="164" height="28"></a>Embed card (static HTML and inline CSS, no JavaScript). Preview:
<a href="https://grokstacks.com/p/odin-claude-plugin/" style="display:block;max-width:380px;box-sizing:border-box;padding:14px 16px;border:1px solid #2a2e3c;border-radius:12px;background:#0a0b0f;color:#e8eaf0;font:14px/1.45 -apple-system,Segoe UI,Roboto,Helvetica,Arial,sans-serif;text-decoration:none"><span style="display:block;font-size:16px;font-weight:700;color:#e8eaf0">Odin Claude Plugin</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#9aa0b1">Community plugin for Grok Build · 40 skills, 4 MCP servers, 28 plugins in this marketplaces</span><span style="display:block;margin:0 0 10px;color:#c9cdd8">Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing…</span><span style="font-size:12px;font-weight:600;color:#7c9cff">View on GrokStacks →</span></a>Markdown summary
**[Odin Claude Plugin on GrokStacks](https://grokstacks.com/p/odin-claude-plugin/)**: Community plugin for Grok Build with 40 skills, 4 MCP servers, 28 plugins in this marketplaces. Install: `grok plugin install odin-core@OutlineDriven/odin-claude-plugin --trust` (after `grok plugin marketplace add OutlineDriven/odin-claude-plugin`)More on badges, embeds and keeping your listing up to date: GrokStacks for plugin authors.
Also in Design
3dicon
One prompt in, a looping animated 3D icon out — with real transparency. A Claude Code skill.
3dviz Pro Max
Agent skill for creative 3D visualization: turn an idea into a Three.js/Blender scene worth exploring. Claude Code + Codex plugin, 223 recipes, 440 knowledge records, 22 proved kits, 37 runnable studies.
Adobe Premiere Pro MCP
Adobe Premiere Pro MCP. Tools for AI-driven video editing via MCP, for Codex, Claude, and other MCP clients.
Agent Sprite Forge
Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.
Agent Storyboard
本地优先的 Agent 视频分镜工作台：让 Codex、Claude Code 通过 MCP 写分镜、生成图片/视频素材和配音，并自动回填。Local-first storyboard workbench for AI agents (Codex, Claude Code).
AI Business Skills
138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, performance, leader ops — plus strategy, personal brand, AI avatar, dropshipping, design master, knowledge library. 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Companion: opa-kit.