Wild Horses plugin for Grok Build

Name: Wild Horses
Author: paulbaranowski

Community plugin, built for Grok BuildPluginProductivity

Analyze code for feedback-loop blockers and AI reasoning gaps, then build, run, and inspect a structured remediation task list to fix what it finds. Ships /harness:feedback-blockers, /harness:reasoning-gaps, and three task-list skills (task-list-builder, task-list-runner, task-list-viewer).

How to install Wild Horses in Grok Build

1. Add this repo as a plugin marketplace in Grok Build (once per computer):

grok plugin marketplace add paulbaranowski/wild-horses

2. Install the plugin:

grok plugin install harness@paulbaranowski/wild-horses --trust

✓ Install-checked in Grok Buildchecked Oct 18, 2026

Review 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 14 plugins; we checked autonomous, harness, linting-hooks. Install another the same way: grok plugin install <name>@paulbaranowski/wild-horses --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 paulbaranowski/wild-horses, then select harness and press i.

Command format: Grok Build's plugin guide

What we checked: on Oct 18, 2026 it installed with grok 1.0.62 and Grok found 7 skills, 3 slash commands, 1 subagent. That's an install check only: we haven't run it in a live Grok session.

What it contains

Skills (7)

task-list-builder — Build or rewrite a structured task list (JSON + paired markdown report) matching the harness task-list schema. Accepts free-form text, an existing reasoning-gaps/feedback-blockers report, an existing JSON task file (in-place rewrite), or re
task-list-runner — Run a structured task list (JSON file in the harness task-list schema) by dispatching each task to a foreground Agent in sequence. Auto-locates an in-progress task file in docs/exec-plans/active/ when no path is given. Use when the user say
task-list-viewer — Read-only viewer for harness task-list JSON files. Auto-locates the active task file in docs/exec-plans/active/. With no args, shows counts, the paired markdown plan path, the in-progress task ID (if any), and pending task titles. With a po
feedback-blockers — Analyze code for feedback-loop blockers — encapsulation gaps, OOP design issues, testability barriers, and harness-unfriendly patterns that prevent fast, clear change-test-fix cycles. Spawns 4 parallel specialist agents, merges findings, an
reasoning-gaps — Analyze code for AI reasoning gaps — untyped signatures, implicit control flow, hidden state, missing docs, and structural complexity that prevent agents from tracing data flow and predicting behavior. Spawns 3 parallel specialist agents, m
autonomous — Autonomously take an issue/ticket or a plan file from a link (or path) to an opened pull request, with no human in the loop. Hand it a Linear/GitHub/other issue URL, a path to a plan/spec file (e.g. ~/plans/repo/foo.md), or a plan already r
install — Install the software the linting-hooks plugin's PostToolUse hooks depend on (prettier, markdownlint-cli2, pyright, jq). Hooks are registered automatically on plugin enable; this command only manages the per-machine software each hook needs

Hooks (1)

hooks — PreToolUse

Plugins in this marketplace (14)

harness — Analyze code for feedback-loop blockers and AI reasoning gaps, then build, run, and inspect a structured remediation task list to fix what it finds. Ships /harness:feedback-blockers, /harness:reasoning-gaps, and three task-list skills (task-list-builder, task-list-runner, task-list-viewer).
autonomous — An autonomous skill that drives a single issue/ticket link or plan file all the way to an opened pull request with no human in the loop: implements, tests, simplifies the diff, runs a bounded reasoning-gaps review (critical only), reviews via wild-pr:review (falling back to an independent sub-agent)
linting-hooks — PostToolUse hooks that auto-format .md files with Prettier + markdownlint and type-check .py files with pyright on every edit. Hooks self-guard when tools are missing; /linting-hooks:install sets up the dependencies per machine.
marketplace — Scaffold a Claude Code plugin marketplace with proper structure, schema validation, and CLAUDE.md conventions. Includes update-cursor-plugins to copy a catalog into ~/.cursor/plugins/local as real files.
pyright — Run pyright on a Python codebase and fix its findings. Supports optional strictness override (basic/standard/strict), persisting the level to config, and progressive ratcheting.
codepath-visualizer — Map and visualize codepaths in any codebase as an interactive architecture diagram. /codepath-mapper extracts call chains from entry points into a structured JSON file; /codepath-visualizer renders the resulting graph as an interactive HTML diagram you can explore in the browser.
plan-keeper — Organize markdown plans in ~/plans/<repo>/. plan-save captures the latest plan from a conversation; plan-do lists and routes a saved plan to the right next superpowers/harness skill based on its shape (idea / spec / impl plan / task-list); plan-done archives a completed plan into ~/plans/<repo>/done
update-git-repos — Pull every configured git repo from origin/<branch> in one shot, using `git fetch` plus `git merge --ff-only` (never `git pull`) so diverged histories never auto-merge silently. Maintains a repo list at ~/.config/wild-horses/update-git-repos/repos.json, supports bootstrap auto-discovery under a root
yes-no-questions-hook — Per-turn UserPromptSubmit hook that reminds Claude to pose decision questions as numbered yes/no questions, collapsing either/or choices into single yes/no items.
steelman — Argue the strongest good-faith case AGAINST the proposed changes in the current conversation or a named design/plan file. A built-in red-team voice that surfaces hidden costs, wrong assumptions, simpler alternatives, second-order effects, and the do-nothing option, so a plan gets stress-tested befor
pr-status-hook — Prints your branch's pull-request link the moment `gh` knows it. A run that spends twenty minutes in CI can no longer finish without printing that link. Also reports at every turn end whether the last commits were actually pushed, and whether the working tree is dirty. Everything comes from real git
wild-pr — Open a pull request with an architecture-first description (via its bundled summary-writer skill), review it, and babysit CI and review feedback. Ships /wild-pr:review for rubric-based code review, /wild-pr:babysit for single-pass tending, /wild-pr for create-then-babysit, /wild-pr:churn to diagnose
cleanup-worktrees — Reclaim disk space from stale git worktrees. Scans configured roots (direct repos and parent dirs), classifies each worktree as cleanable (merged PR, upstream gone, merged into the default branch, or stale) or skipped (dirty, locked, unpushed), shows the cleanable set grouped by reason with sizes, a
plain-language — Apply the plain-language writing standard to prose anywhere in a repo: code comments, docstrings, markdown, plain text, or pasted text. /plain-language:check scans a path, PR, branch diff, or the whole repo and reports long sentences, em-dashes, filler phrases, and figurative tokens; /plain-language

About this listing

Wild Horses is a community plugin on GitHub by paulbaranowski, 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 7 skills, 1 hook, 14 plugins in this marketplaces. Its license is MIT. We checked commit 0b63e0eb7960. It's one of 162 listings in the Productivity category on GrokStacks.

Wild Horses FAQ

How do I install Wild Horses in Grok Build?

Add the repo as a marketplace with grok plugin marketplace add paulbaranowski/wild-horses, then run grok plugin install harness@paulbaranowski/wild-horses --trust. This repo's marketplace has 14 plugins; we checked autonomous, harness, linting-hooks. Install another the same way: grok plugin install <name>@paulbaranowski/wild-horses --trust (names under 'What it contains'). Then start a new Grok session, or press r in /plugins, to load it.

Is Wild Horses an official Grok Build plugin?

No. Wild Horses is a community plugin on GitHub by paulbaranowski, 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 Wild Horses include?

According to what Grok loaded in our install check, Wild Horses includes 7 skills, 1 hook, 14 plugins in this marketplaces: task-list-builder, task-list-runner, task-list-viewer, feedback-blockers, reasoning-gaps, autonomous….

Details

Type: Plugin
Category: Productivity
Source: Community plugin, built for Grok Build
License: MIT
Author: paulbaranowski
Source repo: https://github.com/paulbaranowski/wild-horses
Checked commit: 0b63e0eb7960
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 Wild Horses? Add the badge; it links to this page.

Markdown

[![Listed on GrokStacks](https://grokstacks.com/badge.svg)](https://grokstacks.com/p/wild-horses/)

HTML

<a href="https://grokstacks.com/p/wild-horses/"><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:

Wild HorsesCommunity plugin for Grok Build · 7 skills, 1 hook, 14 plugins in this marketplacesAnalyze code for feedback-loop blockers and AI reasoning gaps, then build, run, and inspect a structured remediation…View on GrokStacks →

<a href="https://grokstacks.com/p/wild-horses/" 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">Wild Horses</span><span style="display:block;margin:2px 0 8px;font-size:12px;color:#9aa0b1">Community plugin for Grok Build · 7 skills, 1 hook, 14 plugins in this marketplaces</span><span style="display:block;margin:0 0 10px;color:#c9cdd8">Analyze code for feedback-loop blockers and AI reasoning gaps, then build, run, and inspect a structured remediation…</span><span style="font-size:12px;font-weight:600;color:#7c9cff">View on GrokStacks →</span></a>

Markdown summary

**[Wild Horses on GrokStacks](https://grokstacks.com/p/wild-horses/)**: Community plugin for Grok Build with 7 skills, 1 hook, 14 plugins in this marketplaces. Install: `grok plugin install harness@paulbaranowski/wild-horses --trust` (after `grok plugin marketplace add paulbaranowski/wild-horses`)

More on badges, embeds and keeping your listing up to date: GrokStacks for plugin authors.

Also in Productivity

Aegis

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

Community Claude Code plugin, installs in GrokPluginProductivity

Agent Deck

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Community Claude Code plugin, installs in GrokPluginProductivity

Agent Skill

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search.

Community Claude Code plugin, installs in GrokPluginProductivity