Workflow and model-routing guidance for multi-agent work: assess (workflow, subagent or single context), route (the role map a workflow script reads from args, keeping fan-out stages off a frontier model), audit-defaults (rechecks bundled defaults against upstream, or sweeps the repo's model and workflow guidance, via a read-only drift-audit workflow), check (whether node resolves and the fetch gate is registered), and setup (writes a user, team or local layer after a preview and a yes).
Slices an existing plan, PRD, or milestone into an executable sprint of dependency-ordered vertical slices sized for one agent run each, with done-when verification per slice; never fabricates a plan. Not for deciding the approach; use architecture.
Convenes several expert perspectives that challenge each other on a design decision with real trade-offs before code is written; quick mode runs a single round. Not for a one-question-at-a-time interrogation of a plan; use grill-me. Not for splitting implementation across workers; use dispatch directly.
Professional Agentic Product Engineering — two skills for operating a coding agent well. /pape:agentic-coach catches teachable moments while you work and surfaces the single most relevant tip from the guide. /pape:harness-audit reads the harness checked into your repo — guidelines, autotests, guardrails — and reports which of the six tiers hold, which don't, and the one next thing to fix.
Write agents, skills, rules, hooks, and MCP servers once, then emit them to every AI CLI in its native format. Installs the CLI, scaffolds specs, imports an existing config, and keeps generated files in sync.
Full product lifecycle orchestrator for SpecKit: research → product-spec → plan → tasks → implement → verify → test → release, across express/lite/standard/v-model modes with human-in-the-loop gates, cross-artifact sync-verify, a living/delta spec with a REQ→…→TEST→EVT traceability matrix, a feature catalog with deterministic retrieval, --dry-run previews, cross-model code review, and brown-field backfill.
Evidence-gated engineering workflows, 7 specialized subagents, and native Rust CDP browser/API automation for AI coding agents across Claude Code, Codex CLI, Antigravity, OpenCode, and DeepSeek Harness (DSH).
Skills, subagent roles, slash commands and an output style from the Model Citizen checkout, installable on their own. Rules, stances, hooks and the Codex projection need `bin/harness install`; see docs/runtime-installation.md.
Pipeline-driven task management for AI coding agents. Tasks flow through backlog → spec → plan → implement → test → review → done stages with dependencies, per-stage artifacts, multi-agent claiming, and the board in the native Claude Code /pipeline pane.
Uniform contributing guidelines for the IOWarp/Clio ecosystem — git etiquette, code style, project architecture awareness, and development workflow standards.
A verification-first development pipeline for Claude Code: brainstorm to plan to phased implementation, with quality gates (verification-loop, code-review, security-review), adversarial review, and TaskTracker-native variants.
The most comprehensive Claude Code plugin — 14+ agents, 56+ skills, 33+ commands, and production-ready hooks for TDD, security scanning, code review, and continuous learning
Cross-session memory for AI coding agents. Git-synced Markdown knowledge base with hybrid semantic + TF-IDF search, typed knowledge graph, confidence/decay scoring, and session auto-distillation with secrets scrubbing. Reads sessions from Claude Code, Cursor, and OpenCode. Browse it in the /knowledge pane.
An auditable, on-disk PDLC state machine for AI software engineering: a staged workflow (PRD → design → TDD → implement → review → ship → retro) with hard contracts + objective checks from real exit codes, so an autonomous loop can drive it to convergence unattended (fail-stop / budget guards) — tool-agnostic, richest in Claude Code, plus Codex via adapters.
Aggregated (not authored here). Ultra-compressed communication mode that cuts ~65% of output tokens (author's measurement), now grown into a 20-skill suite (commit discipline, review, refactor verbs, plus 4 skills — caveman-discover, caveman-manage, caveman-evidence-review, caveman-setup — for the author's hosted Caveman Cloud commercial service). Ships SessionStart and UserPromptSubmit hooks (needs node on PATH; runs on every prompt). General agent behavior. By JuliusBrussee; skills are MIT, the repo also ships a Business Source License 1.1 engine.