Tech stack decision phase for the enterprise pipeline. Auto-detects which technology domains need decisions (runtime, framework, database, auth, etc.), presents options with decision matrices, and locks choices into stack-decisions.json for downstream consumption by enterprise-plan. Incumbent bias for existing…
Evidence-based verification before any completion claim. No 'should work' or 'probably fine' — paste fresh test output or don't claim done. 7-check verification sequence. Use before committing or claiming work is complete.
Use when enterprise work is about to be declared complete and the claim needs fresh evidence, postcondition tracing, and an explicit proof-scope verdict.
Use when starting a feature, significant refactor, enterprise hardening effort, GitHub issue intake/processing, or multi-stage bugfix that needs end-to-end workflow control, portable repo-local artifacts, and explicit proof scope.
Multi-orchestrator fleet management. Takes a batch of tasks, analyzes dependencies and boundaries, assigns optimal models (Opus/Sonnet/Haiku/Worker), sets up isolated worktrees, and dispatches concurrent orchestrators with merge coordination. Use when the user has multiple tasks to parallelize across agents.
Lightweight rapid development workflow. Agent Harness with minimal ceremony. No research agents, no review agents, no TDD enforcement. Just analyze, plan, build, verify. Use for small features, config changes, quick fixes that are too big for "just do it" but don't need the full pipeline. Invoked with /full-cycle-fast…
Research-heavy development workflow. Agent Harness + Compound Engineering deep research. 8+ parallel research agents explore best practices, framework docs, security patterns, and performance before any code is written. Use for unfamiliar territory, new integrations, architectural decisions, or when you want maximum…
TDD-first development workflow. Agent Harness + Superpowers TDD discipline. Every task starts with a failing test. No code without a test first. Use for bug fixes, features where correctness is critical, or when you want maximum test coverage. Invoked with /full-cycle-tdd followed by a description.
Complete structured development workflow combining Agent Harness, Superpowers, Compound Engineering, and Agent Teams. Use when starting any new feature, bug fix, refactor, or development task. Invoked with /full-cycle followed by a description of what to build. Interactive planning then fully autonomous execution.…
Use when turning a diagnose.buildpacket.v1 JSON packet, bug diagnosis, or agent handoff into GitHub issues or issue comments, especially when the user wants ready-for-agent work items created without implementing code.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Use when approaching context limits (70%+ usage), switching tasks mid-stream, ending a session with incomplete work, or when the user says "write a handover", "save progress", "I need to stop", or "context is getting full". Also use proactively when you detect that context compression has started occurring.
Standards-enforcement gate that runs BEFORE implementation. Takes a plan, TDD, or fix proposal and hard-blocks it if SRP, seam, ownership, blast radius, edge cases, or root-cause reasoning are missing. Emits a hardening-report.md that downstream skills (enterprise-plan, enterprise-contract, patch-or-fix, b-deep-debug)…
Install and configure the claude-harness governance system in the current project. Sets up hooks, skills, settings.json, evidence system, Obsidian vault integration, and runs enterprise-discover to produce a stack profile. After this, /enterprise is ready to go. Use when starting a new project or adding the harness to…
Pull latest skills from claude-harness repo and sync to /.claude/skills/ and /.codex/skills/. Run this in any project to get the latest enterprise skills. Use when the user says 'update skills', 'sync skills', 'pull latest harness', or invokes /harness-update.
Oldest-first Helpdesk dev PR queue closeout orchestrator. Use when Ben asks to drain, close out, babysit, green, reply to review threads, or merge eligible open Helpdesk pull requests targeting dev. Requires live GitHub truth, clean isolated worktrees, full PR blast-radius fan-out, patch-or-fix for bugfix or behavior…
Apply final Claude/Codex consensus quality gates for Helpdesk PRs, goals, skills, and workflows before claiming ready, green, done, merge-ready, or workflow-complete.
Use when reviewing, creating, enabling, disabling, or troubleshooting Codex hooks; when hooks may be adding context noise, hidden state, stale disabled entries, or surprise behavior; or when proposing a guardrail hook. Keeps hooks mechanical, low-noise, PreToolUse-first, deterministic, and separate from skill decision…
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
Use when writing or modifying code that interacts with REX (Retail Express), Shopify, or any external integration/sync system. Triggers on work involving SOAP calls, REX API, Shopify API, inventory sync, order sync, product sync, fulfillment sync, or any code in services/retailExpress/, services/shopify, or queue…
Use after GitHub issues are created, discovered, pushed, or handed off and the operator asks "now what", "which issue should an agent do", "make this ready for a build agent", "turn these issues into agent prompts", or "classify the queue". Fetches live issue state, separates intake from proof, routes through…
Standalone single GitHub issue to green PR orchestrator. Use when Codex is asked to target one specific GitHub issue number, owner/repo#number, or issue URL and drive it through a one-subagent-one-job repair workflow into a proved PR. Requires diagnose, blast-radius, patch-or-fix, live GitHub gate discovery…
★not rated 7 2mo agoA104 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: