Plugin Claude Code
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. Hand it a Linear/GitHub/other issue URL, a path to a plan/spec file, or a plan already in the conversation, and it decides everything itself: implements, tests, simplifies the diff…
Plugin Claude Code
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, and removes the ones.
Plugin Claude Code
Map and visualize codepaths in any codebase as an interactive architecture diagram.
Plugin Claude Code
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 two analysis commands (/harness:feedback-blockers, /harness:reasoning-gaps) and three task-list skills (task-list-builder, task-list-runner, task-list-viewe.
Plugin Claude Code
PostToolUse hooks that run Prettier + markdownlint on .md edits and pyright on .py edits. Hooks are registered automatically; /linting-hooks:install detects and installs the required software per machine.
Plugin Claude Code
Apply the plain-language writing standard to prose anywhere in a repo: code comments, docstrings, markdown, plain text, or pasted text. /plain-language:check reports long sentences, em-dashes, filler phrases, and figurative tokens; /plain-language:apply rewrites until the scan is clean while a bundled stdlib CLI…
Plugin Claude Code
A local task-management system built around plans in a /plans/ / tree: a task is a plan that either spawns more plans or gets built into code. Capture from conversation, route to the next step, archive, dispatch via groundcrew, and optionally export to Linear/Jira.
Plugin Claude Code
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/gh state, never fro.
Plugin Claude Code
Run pyright on a Python codebase and fix the errors it finds via the harness task-list pipeline. Phase 3 partitions errors per-file into a structured markdown report; Phase 4 hands off to the sibling task-list-builder + task-list-runner skills for serial, audited fixes with per-task pyright verifySteps and inten.
Plugin Claude Code
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: surfaces hidden costs, wrong assumptions, simpler alternatives, and the do-nothing option, so a plan gets stress-tested before it ships.
Plugin Claude Code
Pull every configured git repo from origin in one shot, using git fetch + git merge --ff-only 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 dir, manual add/remove, and a configurable default.
Plugin Claude Code
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, and the summary-writer skill for architecture.
Plugin Claude Code
Injects a per-turn reminder (via a UserPromptSubmit hook) to ask the user decision questions as numbered yes/no questions — collapsing every either/or into a single yes/no rather than an inline 'X, or Y?' or a pick-one menu. Portable, shareable restatement of a personal CLAUDE.md rule.