autonomous-plan
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
Create or edit the plan file the autonomous scheduler uses so Vodou can work unattended (e.g. overnight).
- Reads credentials
In this repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- board-workerSkill
- board-triage-specifierSkill
- create-a-skillSkill
- execdesk-action-board-prepSkill
- execdesk-action-competitor-monitorSkill
- execdesk-action-competitor-positioningSkill
- execdesk-action-content-calendarSkill
- execdesk-action-decision-frameworkSkill
- execdesk-action-growth-hack-runnerSkill
- execdesk-action-icp-profileSkill
- execdesk-action-quarterly-goals-reviewSkill
- execdesk-action-twitter-thread-drafterSkill
- execdesk-action-weekly-briefSkill
- execdesk-ceoSkill
- execdesk-chief-of-staffSkill
- execdesk-cmoSkill
- think-deepSkill
- docker-compose-devSkill
- calendar-hold-approvalSkill
- chuck-norrisSkill
- email-send-approvalSkill
- graph-ask-demoSkill
- inbox-and-agendaSkill
- meeting-brief-graphSkill
- multi-mcp-testSkill
- schedule-badge-proofSkill
- stopping-point-testSkill
- turn-log-smokeSkill
- code-review-templateSkill
- custom-skill-templateSkill
- daily-research-briefSkill
- pr-review-pipelineSkill
- research-analysis-templateSkill
- ship-a-featureSkill
- browser-toolsSkill
- code-reviewSkill
- deep-thinkingSkill
- first-skillSkill
- helloSkill
- implementation-planningSkill
- install-mcp-serverSkill
- masterySkill
- mcp-builderSkill
- mcp-installerSkill
- morning-briefSkill
- new-user-walkthroughSkill
- oauth-authenticationSkill
- onboardingSkill
- parallel-code-analysisSkill
- project-wizardSkill
- qa-reportSkill
- qa-testingSkill
- regression-testSkill
- self-improveSkill
- self-learningSkill
- skill-developmentSkill
- social-media-marketingSkill
- soulSkill
- The first 60 shown.
The file
Files
Vodou Autonomous Plan — Create a Plan for Unattended Runs
What This Does
The autonomous scheduler runs ./do 'autonomous continue' on a schedule (e.g. every 4h). Each run: the planning step reads a plan file (from .env: VODOU_AUTONOMOUS_PLAN_PATH), asks an LLM for one next task, then runs it. So Vodou can work on itself while you sleep — one task per run.
When adding a scheduled task for autonomous runs, the payload must always be ./do 'autonomous continue', never the text of a plan task (e.g. "Add unit tests for...").
This skill helps you create or edit that plan file and wire up .env and the schedule.
Plan File Location and Format
- Recommended path:
.vodou/workspace/autonomous-plan.md(already created as a template). - Alternative: Any path relative to project root, e.g.
PLANS/0.5.33.3/0.5.33.3.2/VODOU-FULL-BUILD-PLAN.md. - Format: Markdown with a clear Goal and phases/sections of concrete, one-at-a-time tasks. Use
- [ ]checkboxes or "NEXT" so the LLM can pick the next task. Example:
## Goal
Improve Vodou while unattended: tests, docs, small refactors.
## Phase 1
- [ ] Run full test suite and log result.
- [ ] Add or expand unit tests for one module.
- [ ] Update one section of docs from recent memory.The LLM sees this plus recent memory and USER.md/SOUL.md, and returns e.g. TASK: Run full test suite and log result.
Stopping Point 1
What do you want to do?
- Create a new plan — I'll create or overwrite
.vodou/workspace/autonomous-plan.mdwith a template (Vodou working on itself: tests, docs, small refactors). You can edit it after. - Edit the existing plan — I'll show the current
.vodou/workspace/autonomous-plan.md(or the file atVODOU_AUTONOMOUS_PLAN_PATH) and add/change tasks based on your instructions. - Wire up .env and schedule — I'll show you the exact
.envline and schedule commands so the daemon runs autonomous tasks (e.g. every 4h) and uses this plan. - Full overnight setup — Create/confirm plan, set
VODOU_AUTONOMOUS_PLAN_PATH, add recurring task, approve autonomous, and remind you to install/start the daemon.
Reply with 1, 2, 3, or 4.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

