- Home
- Skills
- Agents & Orchestration
- Away Mode
Away Mode
Hand over a task file, walk away and come back to finished work, server-side proof and one handoff report.
Free
Works with the AI Agents you already use
Away Mode
Example session with this skill installed
I'm going to sleep. Finish all 5 tasks in todo.md. You have full authority to handle it while I'm out. Don't ask me anything, just leave the report in HANDOFF.md.
- Read your context and instructions
- Compiled the away mode
I have completed the autonomous run for the 5 tasks listed in todo.md. The session survived one timeout and resumed successfully using .away-mode/progress.json.
Away Mode Handoff Report
| Job ID | Task | Status | Evidence |
|---|---|---|---|
| 01 | Update User schema | DONE | prisma migrate status confirmed schema version 20231027_12 |
| 02 | Fix API auth leak | DONE | curl -I returned 401 for unauthenticated request to /api/admin |
| 03 | Optimize image logs | DONE | du -sh logs/images reduced from 4GB to 200MB via cleanup script |
| 04 | Refactor CSS modules | DONE | npm run build completed; no regressions in dist/assets |
| 05 | Flush Redis cache | BLOCKED | Requires production credentials not found in .env |
Assumptions & Decisions
- Job 01: Used
DateTimefor the newlast_loginfield to match existing conventions inProfilemodel. - Job 03: Set log retention to 7 days as the task file did not specify a duration.
Irreversible Work Pending Approval
The following tasks were prepared but not executed per safety protocols:
rm -rf ./legacy_backups/*: Prepared scriptscripts/cleanup_legacy.shready for execution.docker system prune -a: Command staged; evidence of 15GB reclaimable space generated.
Next steps
- Review the blocked Redis task and provide the necessary environment variables.
- Run
./scripts/cleanup_legacy.shif the legacy backups are no longer needed. - Delete the
.away-modedirectory to clear the session state.
Connects securely to your tools. The creator never sees your data.
About this skill
Development stalls when you are away from the keyboard. This skill allows your agent to work through task lists autonomously while you are asleep or in meetings, making decisions on its own and providing verifiable proof for every completed job.
What it does
- Autonomous execution completes a specific list of tasks from your
todo.mdor backlog without asking for clarification. - State persistence maintains a
progress.jsonfile to ensure the agent can resume exactly where it left off if the session drops. - Verification loops runs actual tests, database queries or API calls to prove changes are live rather than just claiming they are done.
- Automated decisioning resolves ambiguities by following existing project patterns and logging assumptions instead of pausing for user input.
- Detailed handoff generates a
HANDOFF.mdreport with status tables, command output evidence and a list of pending approvals for irreversible actions.
How it works
- The user provides a task file or a list of jobs and signals they are going "away" or "offline."
- The agent initializes a tracking folder, reads project conventions (README, CLAUDE.md), and maps the verification targets.
- The agent enters a loop: planning, applying file changes, verifying on the server/database, and recording evidence.
- If a session interruption is likely, the agent schedules resume triggers to ensure the entire backlog is finished.
Frameworks & tools
Works with any stack that includes a task file (.md, Notion, Drive) and a command-line interface. It specifically integrates with docker-compose, prisma, alembic, and standard Unix tools for file manipulation and verification.
Why this beats prompting it yourself
Standard prompts often stall when they hit an error or an ambiguity, waiting for your reply. This skill enforces a "decide and record" policy and uses persistent state tracking to survive session timeouts, turning your agent into a true overnight worker.
Use cases
- Overnight refactoring to handle repetitive migrations or style updates across a large codebase.
- Unattended deployments where the agent must verify container status and API health after a series of updates.
- Syncing backlogs by working through a
sprint.mdfile while the lead developer is in meetings.
Known limitations
Does not perform irreversible actions like dropping production tables or sending external emails without explicit prior permission. Requires access to a local filesystem or device bridge to maintain the state file.
Requires a task file (or clear list) to start. Will not perform irreversible actions (DROP, payments, DNS) without manual approval. Requires filesystem access for progress tracking.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires
Permissions
File Scopes
Shell, file read/write and network access are used to carry out the jobs in your task file and to verify them (tests, database queries and live API calls). The skill also edits whatever project files your jobs require. Run state lives in .away-mode/ and the final report in HANDOFF.md. Irreversible actions (deleting data, sending messages, payments, DNS changes) are prepared but never executed without explicit permission in the task file.