hstack
claudecodexEntry skill, plan and ship workflows, and the SDLC steps they chain.
15 skills
Claude Code and Codex plugins their authors filed under "workflow". All categories.
Entry skill, plan and ship workflows, and the SDLC steps they chain.
15 skills
Working rules that hold: memory-first work, blind review, one issue per session, and the safety gates that make them real.
9 skills · 5 agents · hooks
Lights-out development workflow: /spec, /next, /fix, /story, /check, /init, the worker agent and the slot scripts.
10 skills · 4 agents · hooks
Sprint specs, risk-tiered review, a refuting reviewer, an exact-candidate release gate, handoffs, and failure-to-rule discipline for AI coding agents.
6 skills · 6 commands · 2 agents
Fluxo multi-agente com sessões persistentes — Arquiteto + time de especialistas file-based, dashboard tmux ao vivo, stream-json parseado em tempo real com emoji, cor e diff visual. Bootstraps um projeto inteiro com Discovery, specs/reports, memória persistente e repo GitHub.
1 skill · 3 commands · 10 agents
Git commands (/commit, /push, /amend), Linear integration, and Pushover notifications.
1 skill · 4 commands · 6 agents · 2 MCP servers · hooks
Domain-blind core harness with 6 agents, GAN-like adversarial evaluation, profile system, sprint contracts, and quantified 0-5 grading
1 skill · 6 commands · 6 agents · hooks
Development control-plane agent surface for Russell's Mini-me Swarm: planner/implementor/reviewer/approver/researcher agents, delivery/review/research skills, and the canonical policy/roles/workflows they follow, self-contained with a layered per-repo config resolver.
9 skills · 5 agents
Orchestrator foundations: generic builder/explorer/planner/reviewer agents, a new-project command, a secret-scan hook, and universal working principles.
5 skills · 4 commands · 4 agents · hooks
Fully agentic software engineering pipeline — from ticket intake through spec design, TDD implementation, code review, and PR creation. Orchestrates multiple agents and skills across five stages.
7 skills · 7 agents
Error monitoring integration — query Sentry issues, traces, and performance data directly from Claude
12 skills · 2 MCP servers
Engineering workflow skills from Matt Pocock — TDD, design, triage, prototyping, and codebase improvement
14 skills
Think a feature through with /dev:design, then plan, build, verify and land code changes through one pipeline — /dev:fix, /dev:task, /dev:feature, /dev:build and /dev:deliver — with approval gates, sequential implementers, a subtractive prune pass and stacked PRs. On request, /dev:review fixes what nobody would argue with and posts the rest that survived a refutation pass as inline PR findings, /dev:fix-pr-comments acts on the unresolved PR threads and asks in chat where a fix needs a choice, /dev:review-and-fix loops the two until review calls the branch finished, /dev:explain-pr explains a PR or a whole stacked chain in plain language, and /dev:update-packages updates every dependency in verified batches and flags the deprecated or abandoned ones. Project-specific checks and git flow come from the project's own verify and git-workflow skills, which /dev:setup and /git:setup write
14 skills
Engineering workflow skills from Matt Pocock — TDD, design, triage, prototyping, and codebase improvement
14 skills
Development control-plane agent surface for Russell's Mini-me Swarm: planner/implementor/reviewer/approver/researcher agents, delivery/review/research skills, and the canonical policy/roles/workflows they follow, self-contained with a layered per-repo config resolver.
9 skills · 5 agents
Multi-agent tmux dashboard with skills, hooks, and workflow automation
8 skills · 5 agents · hooks
Personal workflow commands (pr, interview, to-tickets, implement, todo-minor), review agents (code-reviewer, security-auditor [opus], architect-reviewer) plus working agents (sql-pro, devops-engineer, pr-creator, ci-fixer), and skills (test-driven-development, mockup).
2 skills · 5 commands · 7 agents
Governed, spec-first AI software delivery for Claude Code: an independent server-side rating gate, per-task token metering, premium templates, an audit-grade decision trail and AI-spend chargeback. AgentDev (Tier-2) adds the same governance for building your own agents and prompts, rated and audited server-side. Sign in with your SmartGenie account; plans at https://devgenie.smartgenie.co.uk/portal.
12 skills · 1 MCP server · hooks
Opinionated GitHub workflow: worktree + draft PR flow, self-documenting issues, and an independent PR reviewer bot.
11 skills · 2 agents · hooks
Work-package planning, architecture review and Opus/Implementer(Sonnet) orchestration with an optional separate code-review, project-convention-aware wiki + README documentation, version bump and commit per feature.
2 skills · 8 commands · 3 agents
Token telemetry for Claude Code and Glitch: measure spend by tool, session, model and pipeline. Measurement-only by default; truncation is opt-in and off.
2 skills · 8 commands · 1 agent · 1 MCP server · hooks
One coordinator, role profiles with per-role model pinning, deterministic zero-token checkpoints, launch preflight, and memory that stays with the coordinator instead of following every disposable worker.
2 skills · 4 commands · 6 agents · hooks
Describe an app, get a running app + PR. Auto-triggering design skill + secure Supabase backend, with /designer-workflow:dw-init to set it up in any project.
9 skills · 2 commands · 1 MCP server · hooks
Scrum adapted for teams made of agents: story points become a context budget, planning poker runs blind to detect ambiguity, and the Definition of Done is a list of commands.
2 skills · 6 commands · 5 agents
Spec-driven development with automated review loops
1 skill · 5 commands · 6 agents · hooks
Adopts best-practice blueprints against a person's or a project's actual situation and compiles them into working artifacts, with skills for the full adoption loop and subagents for read-only project surveying and spec validation.
11 skills · 2 agents
SDLC workflow plugins: docs-sync (documentation synchronization), docs-distill (synthesis layer — the summary view nobody rebuilds because nobody asks; discovery + drift signal via `covers:` frontmatter, crystal harvest on cut, two-way handoff with docs-sync), learn (knowledge capture), changelog (project change tracking), crystal-* (multi-root workitem discipline gate — grow/bud/cut/cave/migrate with auto-scan + 4-tier status taxonomy + in-flight capture-reminder + orphan-sidetracks gate + batch legacy-doc migration + evidence discipline: Basis taxonomy, pre-action gate, live current-model section), intercom (central cross-agent/cross-session message store outside all repos, git-remote-identity routing + agent directory: auto-aliases + user-said names + description, SessionStart identity check, hard-stop on unresolved targets), wrap (pre-clean-session check: chat-only items written to their homes, one commit, a start phrase with a slug), retro (do the shared rules work: the owner's turns across every session on the machine, read against the rules each session received), and a lesson folded into the shared rules by a subagent rather than appended — the layer may be rewritten, a change to what sessions receive is shown to the owner first, and a writer installs it only over the version it was made from, with a history of the last 50.
12 skills · hooks
A delivery funnel for one repository task: triage, spec, implement, test, adversarial review, draft pull request. Configured per repo, so the same funnel runs on any stack.
5 skills · 2 commands · 5 agents · hooks
Cross-repository agent-to-agent messaging. Sets this repository up as a Parley agent, keeps its list of peers current, and lets a person manage the files agents share.
1 skill · 11 commands · hooks
All Globaly company skills in one plugin — brainstorming, product deep-research, PRD generation, architecture docs, implementation planning, parallel subagent dispatch, the Globaly design system, and full-dev implementation. Auto-syncs on each session.
12 skills · hooks