18,066 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.
Multi-agent collaboration patterns for Claude Code: orchestrators that fan out across dependent GitHub issues, with one PR per sub-ticket and human-in-the-loop merge gates.
★not rated 2 4mo agoA
tokens not measured
originalMIT
File-based planning with interactive gates and native task tracking. Use when user says /plan, needs to break a complex feature into phases, or wants structured implementation planning with user approval at key decision points. Supports task mode (single plan file) and spec mode (multi-file architecture).
Autonomous timed development shift: agents pick backlog work, run maintenance, impact analysis, QA, UI/UX, performance review, and code review in a loop until duration ends. Use for dev shift, maintenance aplikasi, application audit, or autonomous sprint. Trigger: /dev-shift or natural language prompt.
Add a day's work, and a Next section of the following day's tasks, to the user's Google Doc work log. Use when the user asks to write up a day, update the work log, or fill in missing days.
Agent orchestration, decisions, and organizational memory for Cursor. Review pending decisions, scaffold initiatives, assign work to specialist agents, and render live widgets in-line.
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments and operates only on the current project.
Used to query or process existing approval instances and approval tasks. Use when users mention approval to-dos, agree, pass, complete, reject, return, withdraw or cancel an instance, retrieve for reconsideration, edit approval forms, submit after filling, change handler, add sign-off node, remind, mark an approval…
Full-lifecycle incident management from your IDE. Prevent incidents before deploy, respond in real-time, and learn from post-mortems -- powered by Rootly.
★not rated 1 3mo agoA
tokens not measured
originalApache-2.0
Resolve repository-specific issue context and safely read or change Linear, GitHub Issues, and Jira Cloud issues through the provider-neutral projectissues MCP server or project-context CLI. Use whenever work involves listing, searching, reading, creating, updating, commenting, subissues, issue relationships…
A read-only plugin that maps the locations, progress stages, and dependencies of seven related projects. A dependency is a link showing that work in one project affects or precedes work in another.
Filesystem-driven four-lane kanban board (todo / doing / blocked / done) exposed as a read-only MCP server and a Python API. Works with DeepSeek Harness and any MCP client. Runs locally from the dsh-kanban-mcp Python package.
★not rated 1▲
+1 28d agoA
tokens not measured
originalMIT
CoAligne workflow skill. Use when a user wants an Agent to use shared CoAligne project context: inspect synced files, read Agent sessions, understand teammate activity, send files or sessions to teammates, download cloud files, resolve CoAligne file/session links, or troubleshoot CoAligne Desktop sync.
Read-only Model Context Protocol server for Favro. Give your AI assistant access to your boards, cards, comments and checklists. Runs locally from the favro-mcp npm package.
★not rated 1 1mo agoA
tokens not measured
originalMIT
MCP Server for TimeZest: manage appointments, pending requests, and ticket schedules in Claude. Runs locally from the timezest-mcp npm package. Needs 2 environment variables to run.
A local MCP server for Zentao, a project-management system used to track requirements, bugs, tasks, and test cases. It lets an AI agent connect to those Zentao records through a Node.js package.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Use an on-premises GitHub CLI MCP server to select an isolated GitHub account and work with allowlisted repositories, committed files, issues, pull requests, checks, Actions logs, releases, labels, milestones, and Projects v2. Use for GitHub inspection, review, contribution, or administration requests that require…
Engineering leadership benchmarks, 1:1 playbooks, developer value calculator. 3,400+ sessions. Remote server at www.marian.coach.
★not rated 1 8d agoA
tokens not measured
originalMIT
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: