detritus
🪨 benitogf.github.io/detritus — what detritus does, at a glance: the knowledge base, code intelligence, candyland, and the delivery pipeline.
Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
🪨 benitogf.github.io/detritus — what detritus does, at a glance: the knowledge base, code intelligence, candyland, and the delivery pipeline.
MCP server for AI coding assistants: a curated knowledge base of engineering doctrine (kb_), live codebase exploration (code_), and verified learned memory (skill_*) — plus slash commands that carry work from plan to open PR through one pipeline (plan → build → review → deliver), in-session or via a multi-agent sidecar.
Detritus is an MCP server for AI coding assistants. It exposes a curated
knowledge base of engineering doctrine (kb_* tools) and live codebase
exploration (code_*) — and layers
on slash commands that share one delivery pipeline: plan, build,
review-with-rework, deliver. Those commands run either in your session (/plan,
/smith, /forge, /janitor, /gh-*, /todo, …) or hand off to the
out-of-process candyland sidecar for multi-agent, dashboard-observable
delivery (/candyland, /quest). No flow merges on
its own — the human merge stays the gate.
Ask your AI coding tool to install Detritus from this repository:
please install detritus mcp https://github.com/benitogf/detritus
Or, if your tool supports Markdown links:
please install detritus mcp [benitogf/detritus](https://github.com/benitogf/detritus)
That is the human install path. You should not need to run Detritus as a CLI tool yourself. Manual install details for an assistant or maintainer live in INSTALL.md.
Use Detritus by command name. This table is generated from docs/flows/ (run
detritus --readme); the folder a doc lives in is its category. Internal
building blocks (docs/core/), agent roles (docs/roles/), and reference
material (docs/ooo/, docs/patterns/) are kb_get-only and intentionally
absent — they are not commands.
MCP server for AI coding assistants: a curated knowledge base of engineering doctrine (kb_), live codebase exploration (code_), and verified learned memory (skill_*) — plus slash commands that carry w
ภาพรวม
MCP server for AI coding assistants: a curated knowledge base of engineering doctrine (kb_), live codebase exploration (code_), and verified learned memory (skill_*) — plus slash commands that carry work from plan to open PR through one pipeline (plan → build → review → deliver), in-session or via a multi-agent sidecar.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Detritus ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 MCP server for AI coding assistants: a curated knowledge base of engineering doctrine (kb_), live codebase exploration (code_), and verified learned memory (skill_*) — plus slash commands that carry work from plan to open PR through one pipeline (plan → build → review → deliver), in-session or via a multi-agent sidecar.