cursor-haki
2353Cursor rule Cursor
Haki AI workflow system — structured project init, task planning, TDD-first execution.
37,058 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
Haki AI workflow system — structured project init, task planning, TDD-first execution.
Plugin Claude Code
Bundles 38 skills, 15 commands, 5 agents · 1,813 tokens together
A disciplined workflow plugin for Cursor, Claude Code, et al.: propose-then-implement, tight feedback loops, and stack conventions across all projects and accounts.
zalab-inc/mcp-sequentialthinking
MCP server Claude CodeCodexCursor +2
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
VoytechG/spec-driven-development
Plugin Claude Code
Bundles 5 skills, 3 hooks · 161 tokens together
Per-area active docs plus deliberate history review so humans and agents share useful project context without loading every archive.
JackScammell/Parliament-Of-Chaos
Plugin Claude Code
Bundles 65 commands, 33 agents, 13 hooks · 1,728 tokens together
A council of opinionated AI specialists to plan, build, review, and refine your projects through structured debate and iteration.
MCP server Claude CodeCodexCursor +2
An MCP-based local tool for helping developers build software prototypes. MCP, or Model Context Protocol, is a standard way for AI tools to connect to external tools and data.
Cursor rule Cursor
Defines the standard workflow for Level 3 (Intermediate Feature) tasks, guiding through comprehensive planning, targeted creative design, structured implementation, detailed reflection, and feature-specific archiving.
Skill Claude Code
Autonomous single-phase implementation using Foundry MCP session-step orchestration. Runs one spec phase under unattended posture with strict gate enforcement, deterministic exits, and verification receipts. Use when executing autonomous implementation with the autonomyrunner role and session-step protocol.
Plugin Claude Code
Bundles 11 skills · 1,840 tokens together
Eleven composable Claude Code skills for engineering and productivity: red-teaming, behavior-preserving hardening audits, multi-advisor decisions, CLAUDE.md hygiene, scored UX and anti-slop reviews, six-pager memos, voice-aware writing, session memory, weekly self-improvement audits, and a skill-forge for…
MCP server Claude CodeCodexCursor +2
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents. Runs locally from the mitos-adr Python package.
Skill Claude CodeCodex
Principal-engineer codebase health pipeline, a deliberate pause between features to buy back optionality. Runs five phases. Discovery, a one-concern-per-subagent fan-out over code debt, smells, architectural decay, separation of concerns, spent optionality, doc gaps, oversized units, oracle strength, AI-generated-code…
Plugin Claude Code
Bundles 11 skills, 1 hook · 2,707 tokens together
Keel — an AI fractional-CTO advisor for product builders who don't have a senior technical voice in the room. Eight skills across the founder journey: first-build-scope, feature-decision, tech-evaluation, architecture-review, deep-review (repo-aware four-lens flagship), enterprise-ready, estimate-check…
Skill Claude CodeCodex
End-to-end Jira ticket workflow that manages a cross-functional team of agents to plan, implement, review, and ship work defined by a Jira ticket. Use this skill whenever the user provides a Jira ticket number (e.g., USP-2313, AID-21, CRM-450) and wants the work completed, or when they mention working on a Jira…
Plugin Claude Code
Bundles 2 skills · 184 tokens together
An operating system for cognition: 135 composable Agent Skills that encode transferable thinking procedures (reasoning, decision-making, research, analysis, forecasting, creativity, communication, collaboration, learning, metacognition, ethics), routed through a better-thinking dispatcher backed by a machine-readable…
Plugin Claude Code
Bundles 4 skills, 6 hooks · 334 tokens together
Persist knowledge and plans across Claude Code sessions. Provides /record-knowledge, /plan-task, /review-knowledge, and /recall-knowledge skills.
Plugin Claude Code
Bundles 54 skills, 22 agents · 7,464 tokens together
Opinionated Claude Code skills + agents for AI PMs, engineering managers, TPMs, and senior ICs. Run /bettersense:start to get oriented.
Plugin Claude Code
Bundles 1 skill · 194 tokens together
Claude Code plugin for living blueprints. Turn an idea into a deeply structured, lint-passing, file-backed system plan before writing any code.
Skill Claude Code
Plan Mode — Orchestrator oversees workflow design, execution, autonomous loop, and review. Activated when told "in plan mode.".
Skill Claude Code
Evidence-bound multi-agent council for high-stakes decisions. Scout uses last30days, Advocate and Skeptic debate, Fact Checker uses deep-research Quick mode. Delivers ranked options with #1 marked, dissent preserved, and the condition that would flip the verdict. Use when user says council this, /council, run the…
PabloTheThinker/hermes-insight
Skill Claude CodeCodex
Use when debugging, planning, or a pattern may recur.
Skill Claude Code
Quick user-centric interview to capture requirements from a time-poor stakeholder.
Plugin Claude Code
Bundles 7 skills · 1,149 tokens together
Product manager skill suite for Claude Code — PRD writing, competitor research, daily briefing, HTML prototyping, feature acceptance, UI walkthrough.
Plugin Claude Code
Bundles 14 skills, 18 commands, 4 agents, 4 hooks · 1,131 tokens together
Claude Code harness for product + engineering delivery. From idea to merged PR, one pipeline. Run /harness-kit:install to set it up in your project.
VibeCodingNights/loop-engineering
Skill Claude CodeCodex
Crystallize a one-line objective into a sub-4k GOAL, scaffold a resumable task-hypergraph workspace on disk, and drive it to completion via PARALLEL map->do->review cycles run as Workflow fan-outs, with adversarial review gates, worktree isolation, and honest pass/fail gates. Use when decomposing a repo / refactor /…
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: