claude

toque

Six-stage AI-Native SDLC planning (intent.md, spec.md, plan.md, review.md) with an adversarial verifier-first design gate, plan-linked troubleshooting, and documentation generation.

0 on GitHubby Kyle Whynotv12.0.0MITupdated 2 months agodevelopment
/

Plugin toque from marketplace toque-marketplace in krwhynot/toque. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (5)

  • documentation

    Generate project documentation (ADR, BRD, PRD, README, runbook, release notes, changelog, technical spec). Dispatches to the appropriate template based on document type. Also suggests which document to create based on context. Triggers on - create adr, create brd, create prd, create readme, generate

  • mcp-research

    Knowledge about when and how to use external MCP search tools (Ref, Exa, Perplexity) for documentation lookup, best practices search, code example discovery, and deep research. Use when looking up framework or library documentation, searching for how others solved a problem, finding code examples, c

  • plan

    Start or resume a guided plan that runs the AI-Native SDLC loop. Six stages, Plan, Design, Build, Test, Deploy, Maintain, each committing one artifact the next stage reads (intent.md, spec.md, plan.md, test results, review.md, new intent). Human approval at every gate; codebase writes require your a

  • self-audit-knowledge

    Knowledge about LLM epistemic transparency, claim verification tiers, failure mode flags, cascade risk classification, and evidence basis formatting. Use when stating how confident a finding is, labelling a claim as verified or unverified, flagging an assumption, assessing whether one wrong conclusi

  • troubleshoot

    AI-guided troubleshooting using the 4-phase systematic debugging framework with severity-driven incident triage and containment. Enforces root cause investigation before suggesting fixes. For SEV1/SEV2 production incidents, temporary containment is allowed before investigation. Logs every step, buil

Slash commands (5)

  • /toque:help

    Show all Toque commands, agents, and capabilities. Use when you need to see what's available or explain the plugin to someone new.

  • /toque:plan-export

    Export a plan as a self-contained zip package that another developer can use with vanilla Claude Code (no plugin required). Copies all referenced documents, redacts secrets, includes a CLAUDE.md that auto-bootstraps context, and verifies codebase compatibility on the receiving end. The developer unz

  • /toque:plan-status

    Show status of all active plans or detailed status of a specific plan. Checks for staleness, shows progress, and recommends next action. Pass a plan name for details or no argument for overview.

  • /toque:quick-audit

    Audit any technical plan, spec, or proposal for gaps, risks, and leadership readiness. Reviews the plan across 8 dimensions (problem, architecture, phasing, risk, rollback, timeline, testing, team) and returns a per-criterion verdict (MET/UNMET/N_A) with evidence. Produces a go/no-go assessment and

  • /toque:quick-cleanup

    Clean up a folder of messy documents (PDFs, images, text files, vendor manuals, meeting notes, legacy docs) into standardized markdown and JSON reference files. Guides you through understanding the data first, then cleans it into structured reference material. Automatically creates a plan homebase f

Subagents (1)

  • plan-auditor

    Use this agent to audit any technical plan, spec, or proposal. Verifies a plan against the criterion registry with evidence, reviewing completeness, risk, timeline, rollback, dependencies, team capacity, testing strategy, and go/no-go criteria. Produces a structured audit report with a leadership-re

Hooks (3)

  • SessionStart

    node

  • SubagentStop

    node

  • PreCompact

    node

View source on GitHub

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain toque?

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.

claude & codex pluginslisted