The Loadout's core work board and orchestration loop for Claude Code. Tickets are classified into categories that route each one to a concrete model and effort, then dispatched to token-gated executors; side issues you mention mid-task get captured on the spot, and a live, self-hosted Kanban dashboard spans every project you work in.
Plugin sidequest from marketplace loadout in poindexter12/loadout. Commands read from the repo's manifest — 7 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
boardOpen the sidequest board (live Kanban of your tickets) in the browser
groomAudit a Sidequest board for completed, stale, duplicate, or superseded tickets, then safely close clear cases. Use for board grooming, cleanup, or ticket audits.
sidequestOpen or manage Sidequest tickets and board workflow. Use for board lifecycle work, planning substantial or ambiguous work, and dispatch/integration/recovery. Stay inline for quick edits at a known location, direct questions, or operational requests.
user-storyDrive a feature from a rough request to shipped, integrated work through the Sidequest board, at a depth you choose to match the work: recon, competing architecture proposals judged and merged into one contract, a story holding the complete backlog, one or many parallel executor waves, and a review
verify-disciplineRun tests without burning the clock or the context window: narrow checks while you iterate, the full suite once at the end. Use when running tests, verifying a change, choosing a test command, or when a suite is being re-run repeatedly.
sidequest-diagnostic-probeSidequest dispatch self-test.
sidequest-exec-dispatch-readonlySidequest ticket executor.
sidequest-exec-dispatchSidequest ticket executor.
sidequest-exec-highSidequest ticket executor.
sidequest-exec-lowSidequest ticket executor.
sidequest-exec-maxSidequest ticket executor.
sidequest-exec-mediumSidequest ticket executor.
sidequest-exec-readonly-highSidequest ticket executor.
sidequest-exec-readonly-lowSidequest ticket executor.
sidequest-exec-readonly-maxSidequest ticket executor.
sidequest-exec-readonly-mediumSidequest ticket executor.
sidequest-exec-readonly-xhighSidequest ticket executor.
sidequest-exec-xhighSidequest ticket executor.
boardruns: node ${CLAUDE_PLUGIN_ROOT}/bin/sidequest-mcp.js
node "${CLAUDE_PLUGIN_ROOT}/hooks/worktree-create.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/board-first-reminder.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/inline-work-nudge.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/force-exec-bypass.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-task-output.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-peer-message.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/force-exec-bypass.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/force-exec-bypass.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/force-exec-bypass.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/bind-runtime-identity.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/force-exec-bypass.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-home-delete.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/repeated-command-warn.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-process-signal.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-bash-windows-paths.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-heredoc-isolated.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-powershell-cmd-shims.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-shared-checkout-git.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-destructive-git.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-shared-tree-commit.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/force-exec-bypass.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/guard-worktree-isolation.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/quota-fallback.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/stop.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/compaction-policy.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/post-compact.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/registry-writer.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/session-end.js"
node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-start.js"
Set up a project from your existing Claude Code habits, keep Loadout installs healthy, and find missing capabilities after real work accumulates. Local scripts reduce session history to a bounded summary before the active model sees it; setup, resupply, updates, and config changes happen only with your approval.
4 skills · hooks
Your ChatGPT/Codex and Grok subscription models in Claude Code's /model picker. A local gateway routes claude-gpt-* models to OpenAI's Codex backend, claude-grok-* models to Grok, and everything else to api.anthropic.com, so you switch between Claude, GPT-5.x, and Grok mid-session like any other model. No API keys.
3 skills · hooks
A self-maintaining codebase map: atomic docs Claude loads at the start of each session and keeps in sync as the code changes. Any stack; greenfield or existing.
2 skills · hooks
Project rules in .claude/rules/*.md, the directory Claude Code reads natively, one rule per file scoped by a paths: glob list. No manifest and no sync step: Live Rules adds timing only, re-grounding a rule when its content changes mid-session and delivering keyword-scoped rules Claude Code cannot trigger on its own. Disable a rule by renaming it to .md.off.
2 skills · hooks
Local, metadata-only telemetry for Claude Code. A bundled observer records session, tool, and subagent lifecycle events into SQLite on your machine, an optional statusline shows live context and usage, and an OpenTelemetry Collector can forward redacted signals to Grafana, generic OTLP, or PostHog. Prompts, responses, code, tool inputs and results, credentials, and environment values are never stored. Every sink beyond local SQLite is opt-in.
1 skill · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.