Agentic Task System — Git skill for Claude Code
CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg: facts from any source.
How to install Agentic Task System
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open renezander030/agentic-task-system and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentic Task System does
CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg: facts from any source, human-ratified. Recommended engines: Graphiti (server), LadybugDB (embedded).
Alternatives in Git
- Self Reflect — Extract learnings from recent PR reviews, conversations, and session patterns to update the knowledge base 402 ★
- Memorix — Open-source cross-agent memory layer for coding agents via MCP 392 ★
- Publish MCP Server — Publishes one of the bundled MCP servers to npm 238 ★
README
Your task manager is the best agent memory you're not using.
`ats` is an **MCP server and CLI that keeps AI-agent context in the task systems you already maintain** — TickTick, Taskmaster, Beads, Obsidian, Notion, GitHub, Airtable, Google, or several at once through the [composite adapter](packages/adapter-composite/). It retrieves relevant tasks, notes, decisions, and runbooks with provenance, then can write results back when the active adapter supports writes. Works with Claude Code, Claude Desktop, Cursor, and any MCP client.
**Adapter, not migration.** Your task app, repository, or vault remains authoritative. ATS maps that source into a common task contract; optional caches and vector indexes improve retrieval but never become a second record that people must edit. It is **task-first**: the task is the spine, while supporting material such as GitHub issues and Notion specs is retrieved as context behind it.
**Two layers, one CLI: tasks and a knowledge graph.** The task layer is record-based on purpose — every entry lives in one backend's projects and fields, and that backend stays authoritative. A record-based layer structurally cannot hold the other thing agents accumulate: durable knowledge **written from any source, about mixed sub
Related Skills
Knowledge Graph
Built on Anthropic internal engineering practices and Karpathy's AutoResearch methodology. A zero-dependency,
Pharn Dev Memory Promote
Prepare and GATE the promotion of ONE lesson/pattern to the canonical memory-bank. It automates the MECHANICS
Code Analysis
by kingler - Provides a menu of advanced code analysis commands for deep inspection, including knowledge graph
Novgraph
A live knowledge graph of your codebase for coding agents: commit intent, co-change coupling, ranked blast rad
Twin Sparrow Apps
Use installed Codex app connectors for Twin Sparrow-focused work. Trigger when the user asks to use Codex Apps
Pvc Git Commit Message Local
Claude Code skill that writes a git commit message in the PVC format (vX.Y.Z headline plus one bullet per real
Related Agents
Brain Keeper
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatib
Curator
(/auto) Maintain active research-tree memory: absorb reviewed evidence, keep graph/state/provenance coherent,
Brain Eval Engineer
Evaluation engineer — question set tooling, layered metrics (harvest/graph/retrieval/answer), fixed-strategy a
