agentplane
v0.2.25
Published
Agent Plane CLI for task workflows, recipes, and project automation.
Maintainers
Readme
agentplane
Agent Plane is a policy-driven framework for running LLM agents inside real repositories. It turns "AI magic" into an engineering process: explicit approvals, role boundaries, and a reproducible execution pipeline. The goal is simple: make agents boring, safe, and auditable.
Why Agent Plane
- You want agents that behave predictably inside real repos.
- You need human approvals, clear roles, and traceable artifacts.
- You want guardrails by default, not optional add-ons.
- You want an offline-first CLI that keeps state local and inspectable.
5-minute start
Install and initialize the CLI:
npm install -g agentplane
agentplane init
agentplane quickstartagentplane init is human-oriented: interactive onboarding includes workflow/backend selection,
execution profile selection (conservative|balanced|aggressive), approval toggles, and optional recipes.
Create your first task and run the workflow:
agentplane task new --title "First task" --description "Describe the change" --priority med --owner ORCHESTRATOR --tag docs
agentplane verify <task-id> --ok --by ORCHESTRATOR --note "Verified"
agentplane finish <task-id> --author ORCHESTRATOR --body "Verified: done" --result "First task completed"Prefer npx instead of a global install?
npx agentplane init
npx agentplane quickstartWhat gets installed automatically
.agentplane/is created with config, tasks, agents, and caches.AGENTS.mdis created if missing and defines the policy/guardrails.- Built-in agent definitions are copied into
.agentplane/agents/. - Optional recipes can install additional agents when you run
agentplane recipes install .... .agentplane/config.jsonstores execution defaults underexecution(profile, reasoning effort, tool budget, safety gates).
Upgrade review reports
After agentplane upgrade (auto or agent-assisted mode), a machine-readable review report is written under .agentplane/.upgrade/:
- Agent mode:
.agentplane/.upgrade/agent/<runId>/review.json - Auto mode:
.agentplane/.upgrade/last-review.json
If any entry has needsSemanticReview: true, treat it as a signal to create an UPGRADER task to perform a semantic prompt merge.
Guardrails and artifacts
- Approval gates for plans and network access (configured in
.agentplane/config.json). - Role boundaries (ORCHESTRATOR, PLANNER, CODER, INTEGRATOR, etc.).
- Agent definitions in
.agentplane/agents/. - Task records in
.agentplane/tasks/with a snapshot export in.agentplane/tasks.json. - A visible, reproducible pipeline:
Preflight -> Plan -> Approval -> Tasks -> Verify -> Finish -> ExportFeatures
- Policy-first execution with explicit approvals and guardrails.
- Role-based workflows for teams: ORCHESTRATOR, PLANNER, CREATOR, INTEGRATOR, etc.
- Two workflow modes:
direct(single checkout) andbranch_pr(worktrees + integration). - Task tracking, verification, and exports baked in.
- Recipes for repeatable setup and automation.
Install
npm install -g agentplaneOr run without installing:
npx agentplane --helpRequirements
- Node.js >= 20
Common Commands
agentplane --help
agentplane quickstart
agentplane role ORCHESTRATOR
agentplane role UPGRADER
agentplane config show
agentplane task list
agentplane task new --title "..." --description "..." --priority med --owner ORCHESTRATOR --tag docs
agentplane verify <task-id> --ok --by ORCHESTRATOR --note "Verified"
agentplane finish <task-id> --author ORCHESTRATOR --body "Verified: done" --result "Task completed"
agentplane recipes listDocs and Guides
- Documentation index: https://github.com/basilisk-labs/agentplane/tree/main/docs
- Workflow overview: https://github.com/basilisk-labs/agentplane/blob/main/docs/user/workflow.mdx
- CLI commands: https://github.com/basilisk-labs/agentplane/blob/main/docs/user/commands.mdx
- Project layout: https://github.com/basilisk-labs/agentplane/blob/main/docs/developer/project-layout.mdx
- Recipes: https://github.com/basilisk-labs/agentplane/tree/main/agentplane-recipes
Support
- Issues: https://github.com/basilisk-labs/agentplane/issues
- Contributing: https://github.com/basilisk-labs/agentplane/blob/main/CONTRIBUTING.md
License
MIT
