Workflow plugins

Everything I want in every project: /core:init-dev-kit, /core:plan, /core:changelog, /core:release, /core:commit, /core:new-project, /core:announcement, /core:report-verify, /core:docs-sync, plus always-on senior-engineer, ai-engineer, nlp, evals, fastapi and flutter standards, code-reviewer and researcher agents, opusplan model routing, a rate-limit status line, and a prettier auto-format hook.

20 skills · 2 agents · hooks

One end-to-end dev workflow for every task, feature, bug fix, refactor, redesign, debug, or research. Replaces multi-skill ceremony with a single per-task markdown work-doc that captures spec, plan, progress, review, and post-mortem in one file. Latest tagged release, the stable channel.

7 skills · 2 commands · 10 agents · hooks

Bleeding-edge hackify, tracks the `main` branch directly. SUPPLY-CHAIN NOTE: unreleased commits (including any new executable code under `hooks/` and `scripts/`) land in your plugin tree on every plugin refresh, with no tag pinning or signature verification. A force-push or compromised maintainer commit reaches you the next time Claude Code refreshes the marketplace. Install ONLY if you accept that risk and read every diff. Production users MUST pin to the `hackify` channel (latest signed tag) instead.

7 skills · 2 commands · 10 agents · hooks

Eä Workflow plugin — agent-driven development skills and hooks.

19 skills · hooks

21 SDLC skills spanning the definition → build → verify → review → ship path, plus security hardening and a shelf of reference and thinking-aid skills.

20 skills

EPCC (Explore-Plan-Code-Commit) systematic development workflow with 12 specialized agents for exploration, planning, coding, and commit phases

7 commands · 12 agents

Kit SDD del equipo: skills de proceso agnósticas y plantillas.

14 skills · 3 agents · hooks

Multi-agent engineering workflows with spec-driven quality gates, safety hooks, and structured verification.

4 skills · 13 agents

AI coding agent discipline: research, planning, self-checks, completion verification, git/CI workflow, package-manager and security rules. Skills only; install the hooks plugin for enforcement. Requires superpowers plugin.

17 skills

Korean-first agentic coding harness: plan, implement, chain-plan, pr (babysit/ship), karina-systematic-debugging, 2-stage review subagents, PR verifier subagent, wiki page writer subagent. Safety hooks run on pwsh 7 / Windows PowerShell, cross-platform (Windows verified, macOS/Linux experimental); skills work on any OS (chain-plan needs the Karina app on Windows).

11 skills · 4 agents · hooks

Engineering-craft skills: red-green TDD, a flaky-test rate, diagnosis, doubt review, grilling, a merge check, grounded research reports, HTML reports, skill linting and a staged-diff column budget. TDD, the merge check, skill lint, column budget and HTML report end in a script's exit code; the flaky-test rate is computed and printed, and sets no exit code; doubt review, grilling, diagnosis and the research verdicts are model-judgment. Auto-composed by the dossier plugin at its phase gates when both are installed — fully functional standalone.

11 skills · 4 agents

Local Grok CLI delegation: task, review, resumable history, best-of-n tournaments, background jobs, stats, and setup health checks.

11 skills · 2 agents · hooks

A delivery funnel for one repository task, in three lanes by what the change can break: spec, tests before the code on risky paths, the repo's own gates, a review whose findings are verified before anything is fixed, draft pull request. Configured per repo, so the same funnel runs on any stack.

6 skills · 2 commands · 5 agents · hooks

First party local Codex CLI delegation for tasks, reviews, resumable threads, and durable background jobs.

11 skills · 1 agent · hooks

Luc tools for Claude Code with status line, schemas, and workspace utilities

7 skills · 3 commands · 3 agents

Claude Code Higher Agents — build ONE feature thoroughly with a deep red-teamed plan, SDD per-task loop, risk-scaled pre-PR gate, independent review, feedback handling, gated merge, conflict resolution, and cleanup. Requires superpowers; model-agnostic

9 skills · 2 agents · hooks

Multi-model orchestration: tier agents, routing rules, blind panel, ultra fleet, model config, and drift doctor.

7 skills · 4 agents · hooks

Development workflow skills for the jackin project: spec-driven feature workflow, pull requests, research, release management, validation, and changelog generation

11 skills

General building skills — grill-me, write-prd, tdd, and more. Project-agnostic skills that enhance any workflow. Required companion for the bugbook plugin's active spec grilling.

11 skills

Simple Agents for Claude Code — command-free skills + subagents for fast single-feature development: plan, approve, isolate in a worktree, implement, PR — Sonnet build and review, Opus only for risky surfaces

7 skills · 3 agents · hooks

NCC — 15+ agents, 15+ skills, 10+ slash commands for spec-driven Next.js & React development

9 skills · hooks

Bugbook workflow skills — flow, ticket, go, prep, catchup, and supporting tools for running the Bugbook app as a project management system.

10 skills

Cooperate Agents — Claude×Codex loop: red-team a milestone plan, implement test-first on a draft PR with Claude checkpoints, run a blind-Claude plus bounded offline single-agent Codex final review, promote only on a validated verdict, then merge and clean up worktrees

10 skills

Spec Kit workflow skills — specify, clarify, plan, tasks, analyze, checklist, implement, constitution, taskstoissues, and agent-context updates. Operates on the .specify/ machinery in the project you invoke it from.

10 skills

Run a single coding agent on a task via tmux + git worktree. /run auto-entry performs a short repo + task recon, then dispatches to /solo. /solo runs one agent in a fresh worktree with a gated 7-phase workflow (Recon, Clarify, Reviewer-Readiness, Plan-Check, Implementation + bullet commits, Final-Verify, Persist, Commit hygiene, Auto-Squash-Merge). Gates run independent adversarial checks: claude subagents plus `codex exec` where applicable (different model family, fresh context, no pane setup). Phase 7 auto-squashes bullet commits onto base, deletes the feature branch, removes the worktree and per-worktree Cargo target, and pings DONE-MERGED so sequential chained runs always start from a clean base. Includes the orchestration script, the tmux-pair-orchestration skill, PROJECT.md care, scoped subagents for the gates, sender identity prefixes, explicit parallel-plan markers, auto-detection of repo-specific subagents (`.claude/agents/<repo>-*.md`) listed in every briefing, shipped guidance templates for 7 stacks, bundled companion skills (gepa for prompt-optimization, dg for adversarial code review), and opt-in pi as a bulk-work coding agent. `/run` defaults to codex and switches to claude only for recon-heavy/plan-integration/greenfield/compliance profiles. Multi-pane spawn modes were removed in 0.19.0.

3 skills · 2 commands · 5 agents

Phase-scoped engineering workflow: single-file DOSSIER.md, cross-repo state, drift detection, resumable builds, evidence log. Composes the whetstone plugin at phase gates when installed (doubt, TDD proof, merge check, skill lint) — fully functional without it.

7 skills · 3 agents

Install first — bootstrap marketplace and harness wiring via /toolkits-initial-setup (HITL). OpenCode: npx @chimeranext/better-toolkits setup.

7 commands · 1 agent · hooks

TDD workflow with 6 specialized agents for test-first development, red-green-refactor cycle, and comprehensive quality analysis

2 commands · 6 agents

Create and query project wikis with optional maintenance automation.

8 skills

Claude acts as a PM under T3 Code: plan, get sign-off, decompose into stories, and run build, review, verify and ship through T3 child roles.

8 skills