Marketplace for jons-plan - a long-running agent harness for Claude Code
npx claudepluginhub jonmmease/jons-planLong-running agent harness with task management, progress tracking, and parallel task execution
A Claude Code plugin inspired by Anthropic's Effective Harnesses for Long-Running Agents blog post for managing complex, multi-session coding tasks.
curl -LsSf https://astral.sh/uv/install.sh | sh)brew install graphviz)npm install -g @openai/codex)npm install -g @anthropic/gemini-cli)Install via Claude Code's plugin marketplace:
/plugin marketplace add jonmmease/jons-plan
/plugin install jons-plan@jonmmease-jons-plan
Then restart Claude Code and test with /jons-plan:status.
When AI agents work on complex projects that span multiple context windows, each new session starts with no memory of what came before. This plugin solves that problem by providing:
For detailed architecture documentation, see docs/architecture.md.
The plugin uses a two-agent architecture:
/jons-plan:new)Creates the infrastructure for a new plan:
request.md with the refined/approved request/jons-plan:proceed)Works incrementally on tasks across sessions:
in-progress tasks firstWorkflows with planning_panel = true use three independent agents to generate plans in parallel, then a senior synthesis agent reviews all three and produces the definitive plan:
The synthesis agent has full authority to investigate the codebase, dismiss incorrect concerns, add missing elements, and restructure the plan. It is not a mechanical merger — it is the decision-maker.
| Command | Purpose |
|---|---|
/jons-plan:new [topic] | Create new plan (auto-suggests workflow type) |
/jons-plan:plan [feedback] | Refine the active plan |
/jons-plan:proceed | Start/continue implementing tasks |
/jons-plan:switch [name] | Switch to a different plan |
/jons-plan:status | Show all plans and task progress |
/jons-plan:viewer | Open the workflow viewer |
Use --workflow <name> with /new to specify workflow type explicitly.
| Workflow | Purpose |
|---|---|
implementation | Build features, fix bugs with research and validation |
direct-implementation | Simple plan-implement-verify for familiar code (no research) |
design | Research, explore, produce design.md |
design-and-implementation | Design first, optionally implement after approval |
deep-implementation | Thorough research + external review before implementation |
dynamic | Research-first, phases generated based on codebase exploration |
iteration | Iterative execute-evaluate-generate loops for long-horizon goals |
review-tour | Generate guided PR review tour from a GitHub PR URL |
code-review | Review code changes + generate PR description |
pr-review | Review existing PR description for quality |
deslop-pr | Detect and remove AI-generated patterns from PR descriptions |
tech-docs | Technical documentation with multi-source research |
tech-docs-review | Review RFCs, design docs, proposals with structured criteria |
Auto-selection: When no --workflow is specified, the plugin analyzes your request and suggests the most appropriate workflow.