buy-vs-build
2473Cursor rule Cursor
Before writing code, decide whether the work should be bought, reused, or built.
37,131 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Cursor rule Cursor
Before writing code, decide whether the work should be bought, reused, or built.
Plugin Claude Code
Bundles 8 skills, 5 commands, 1 agent · 1,536 tokens together
A Lean business-development coach: guide a venture through Running Lean — Lean Canvas, riskiest-assumption testing, customer interviews, experiments, and product/market fit — and role-play the customers, investors, and advisors you test it with.
Plugin Claude Code
Bundles 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers · 1,776 tokens together
Senior engineering team in a plugin: one clear workflow (mission → brief → plan → build → verify → ship), 19 specialized agents, quality-gate enforcement, and CI. Language-agnostic.
gabriele-mastrapasqua/codex-lean-team
Skill Claude CodeCodex
Route software-engineering tasks to the smallest useful workflow. Trigger for ambiguous, multi-module, risky, performance-sensitive, AI/ML, or infrastructure work; skip for trivial edits.
Skill Claude CodeCodex
Multi-agent orchestration engine for complex tasks. Use when you need to break a complex query into subtasks, run them in parallel with a DAG engine, and synthesize results. Triggers on: multi-agent, parallel execution, orchestrate, DAG, decompose task, dynamic workflow.
Command Claude Code
Plans, implements, reviews, and finalizes a thread in a single run without requiring prior setup.
Skill Claude CodeCodex
Propose a reviewable multi-agent workflow as a blueprint — pick and name the pattern (map-reduce, pipeline, tournament, loop-until-dry, dag), emit its shape as an agentstack-blueprint JSON block, and WAIT for the user to approve / reject / edit before authoring and running it via agentstack more workflow run.
Skill Claude CodeCodex
Use when executing implementation plans via cmcs/Codex agents with structured review checkpoints.
AgileLuminary/mcp-agile-luminary
Cursor rule Cursor
User: "Let's work on the next user story.".
Cursor rule Cursor
When starting a new feature, document specifications and technical design and implement them step by step.
Cursor rule Cursor
POC development and technical validation with mandatory questionnaire.
Cursor rule Cursor
Entry point for the disciplined reasoning pipeline. Invoke to make a cheap model plan, implement, self-critique, and verify with hard no-premature-done gates.
Cursor rule Cursor
This rule generates technology-specific base PRP templates (prp-base-{tech}.json and prp-base-{tech}.md) from PRPs/INITIAL.md files. It uses the embedded canonical template and overlays tech-specific content for project-wide implementation.
Cursor rule Cursor
A set of rules for an automated CodingPlan workflow that processes requirements when a user or CodingPlan tool starts the process.
michaelpersonal/compound-engineering
Cursor rule Cursor
Based on Every.to's Compound Engineering.
Agent Claude Code
Turn requirements and exploration results into a structured, executable step-by-step plan. Write to the session-scoped plan file. No implementation code.
Skill Claude CodeCodex
Decomposes PRDs and feature briefs into spine task packets (PROMPT.md, STATUS.md) under spine-tasks/ for autonomous execution via spine batch. Use when asked to "create a spine task", "decompose a PRD", "stage tasks for spine", "write PROMPT.md for spine", "create SP- tasks", or queue work for spine workers.
Plugin Claude Code
Bundles 3 skills, 2 agents, 1 hook · 145 tokens together
Assess RFEs and Initiatives against quality criteria using structured rubrics.
Plugin Claude Code
Bundles 1 skill, 11 commands, 6 agents · 279 tokens together
6 engineering management agents for Claude Code. Spec generation, ticket decomposition, risk detection, review orchestration, release management, and sprint retrospectives.
Skill Claude Code
Documento funcional resumido em português brasileiro (Cenário, RFs do que muda, UCs em passos com referência a RF e diagrama Mermaid, Impactos, Critérios de aceite para agentes de IA); analista/PO que questiona e não presume; entrevista grill-me sem rascunho até entendimento completo; o DERS descreve o delta e…
Plugin Claude Code
Bundles 17 commands · 130 tokens together
Solokit - Structured Solo Development with AI and Quality Automation for Claude Code.
fshot/claude-plugin-hackathoner
Plugin Claude Code
Bundles 14 skills, 1 command, 2 agents, 1 hook · 1,480 tokens together
Structure your next hackathon, game jam, or sprint with Claude Code — plans before code, storytelling from brainstorm to demo, checkpoint discipline.
Plugin Claude Code
Bundles 13 skills, 10 agents · 1,076 tokens together
Agent workflow skills for spec writing and review, plain-language engineering text, code review, decision audits, PR feedback, self-review, PR publishing, visual PR explanations, and narrated lecture videos.
Plugin Claude Code
Bundles 2 skills, 1 agent · 312 tokens together
PEP (Project Enhancement Proposal) workflow: markdown-driven planning, investigation, and execution with wave shapes, adversarial review, and gate evidence. Audit hook records what actually ran. No engine, no state.db. Folds in the spike (investigation) flow. Includes the grill skill (alignment interview + domain…
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: