Developer Tools plugins

Code quality and security review with DevSift

1 skill

Generate and verify Java services with the shared MVC/JPA, WebFlux/R2DBC and experimental local AI starters.

1 skill

Use Google's Antigravity CLI from Codex on native Windows.

1 skill

灵枢记忆：18 条工作纪律 skill + 长期记忆系统（mdcg MCP）接入

1 skill

Supervised collaboration rooms for coding agents: shared discussion, tasks, replay and usage observations.

1 MCP server

A small notebook that demonstrates a Codex plugin with an OpenAI UI.

1 skill

Evidence-backed code scorecards for .NET, JavaScript/TypeScript, and the Python preview.

1 skill

agent to agent comms

1 skill

QP's preferred stacks, tools, project layouts and architecture defaults

1 skill

Install and operate the SMR local routing daemon for Codex and Claude Code.

1 skill

Observability plugin for Claude Code with MLflow tracing

★ Developer bundle — workbench + mentor (meta, stub)

Multimodal transit visualization tool by Las Vegans for Better Transit.

Install obra/superpowers directly from upstream for Codex, Pi, OpenCode, and Claude Code. Stay on a known-good release or commit, try a branch, and upgrade when you choose.

Official DotMoose MCP endpoints, portable plugin manifests, registry metadata, and usage guides.

Open GitHub pull requests and GitLab merge requests in lgtm from Claude Code: a button under replies that link one, and /lgtm

SSH hosts in project and global scopes, encrypted credentials, and ssh2-based exec, resumable transfers, tunnels, background jobs and a live pane.

Observability plugin for Claude Code with MLflow tracing

Harness-native ECC plugin for engineering teams - 71 agents, 311 skills, 97 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses

200 skills · 97 commands · 71 agents · 1 MCP server · hooks

Harness-native ECC plugin for engineering teams - 68 agents, 293 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses

200 skills · 94 commands · 68 agents · 1 MCP server · hooks

265 development skills adapted from Mindrally, with individually reviewed technical guidance and progressive disclosure for Codex, GitHub Copilot and Claude Code.

200 skills

169 coding-agent skills with 575 declared refusal boundaries.

169 skills

Self-contained local plugin and skill creation, discovery, evidence, evaluation, risk review, conversion and deterministic packaging. Host execution capabilities and explicit public lookups remain separate.

95 skills

Turns big code changes into a checked, repeatable workflow. Five phases (assess, plan, execute, review, iterate), plus an optional learn phase. Splits work into parallel chunks where it can. Picks the right model for each task. A strong model plans and reviews. A faster model writes code. A small model does pattern checks. Catches the common ways big changes go wrong. The diff drifts from the plan. The implementer makes quiet design calls you never see. Tests pass but pages do not render. Fake data leaks into production. Plans must list every design decision up front. The implementer must say which decisions it made. A lint compares the claim to the actual diff. Work with six or more design decisions auto-routes to the strong model in one pass. A read-only critic runs before full validation. Cheap checks catch the obvious mistakes first. Includes an optimize mode that runs multiple tests in a single experiment using Design of Experiments. You can test six variables at once instead of one. The mode plans the test matrix, runs each combination, and tells you which variable actually moved the number. Bundles a debugger memory and an architecture engine that maps the codebase before each build. Use it for features, refactors, migrations, schema changes, anything that touches more than one file. Skip it for fixes under about 20 lines. Verifies the production deploy after a push (Vercel): polls the deployment to a terminal state and probes changed routes — an auth-gated 401/403 is healthy, only a 5xx or build error fails. An independent commit auditor runs at the git-commit boundary on every commit (manual user, Codex, build-loop, IDE) and gathers its own context from intent, goal, PRD, and constitution — the running session renders one of four verdicts in conversation: yay, nay, suggest correction, look again.

60 skills · 2 commands · 29 agents · hooks

No description.

86 skills

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

57 skills · 27 agents · hooks

Shape work with the user into tickets, then build each ticket with deliberate subagents, simple code, and verified evidence. pstack's way of building (Lauren Tan, via the pstack-claude port) merged with Matt Pocock's grilling, specs, and tickets.

74 skills · 4 agents

If you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence. Original pstack by Lauren Tan (poteto).

71 skills · 4 agents · hooks

If you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence. Ported from cursor/plugins/pstack to Claude Code. Original pstack by Lauren Tan (poteto).

67 skills · 4 agents · hooks

if you want to go fast, go deep first. bleat helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.

67 skills · 2 agents · hooks