Contextgraph Claude Code Plugin
ContextGraph Claude Code Plugin is a Claude Code plugin for the Build phase that provides AI-forward persistent task management via a living, executable context graph.
by contextgraph · github.com/contextgraph/claude-code-plugin
Install the ContextGraph Claude Code plugin to keep a living, executable task graph that ties planning, context, and agent execution in one persistent layer.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install contextgraph-claude-code-plugin@contextgraph/claude-code-pluginBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:contextgraph/claude-code-plugin") and the paste-ready config with skillselion.get_install_config("plugin:contextgraph/claude-code-plugin").
What it does
ContextGraph for Claude Code is a one-plugin package focused on persistent, graph-shaped task management for builders who plan in the agent and execute in the same flow. Rather than flat checklists that rot in a markdown file, the plugin narrative emphasizes a living context graph—ideas become plans, plans become executable nodes, and execution feedback can refine what comes next. That is valuable for solo founders juggling validation spikes, build tasks, and ship checklists without a separate PM tool. The planning category and keywords (executable, execution, living plans) signal intermediate setup: you are adopting a new mental model for how Claude Code holds state, not just adding a formatter skill. It pairs well with long-horizon products where task dependencies and rationale matter. It is weaker when you only need a single-shot script or when your team already standardizes on Jira with no agent integration. Register it when you want Claude Code to own the plan graph and make every session smarter against that structure.
Highlights
- Single ContextGraph plugin for Claude Code with graph-based persistent tasks
- Living planning layer where ideas, plans, and execution stay linked
- Executable execution graph so work items improve as the agent runs them
- AI-forward task management positioned as smarter than vibe-only todo lists
- Transforms scattered context into a structured graph every session can reuse
Why builders use it
Plans and tasks live in disconnected notes while Claude Code sessions lose the graph of what depends on what and why.
After install, planning, context, and execution share one persistent graph so the agent can run and refine work against structured tasks instead of ephemeral prompts.
At a glance
- Type - Plugin in Productivity.
- Adoption - 0 installs, 1 stars, 0 votes.
FAQ
Who is contextgraph-claude-code-plugin for?
Indie developers and agent-first builders who want Claude Code to manage ongoing tasks, plans, and execution context in one graph.
When should I use contextgraph-claude-code-plugin?
Use it when you have multi-step products, living roadmaps, or recurring agent sessions and flat todos no longer capture dependencies and context.
How do I add contextgraph-claude-code-plugin to my agent?
Install the contextgraph/claude-code-plugin repository as a Claude Code plugin, enable ContextGraph per the repo README, then create or import your task graph before relying on it across sessions.
Comments
Share how you use contextgraph-claude-code-plugin, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.