elves
Enables asynchronous development workflows where coding tasks progress without developer attention, reducing iteration cycles and freeing engineers to focus …
An Agent Skill for autonomous, multi-batch development: you write the plan and own the merge decision; the agent executes large development plans unattended — with testing, review, and documentation — while surviving context compaction across long runs. A coordinator called Cobbler decides whether to answer directly, ask independent reviewers, or assign scoped worker agents. Runs are staged first (plan, branch, PR, survival guide), then launched in a separate prompt.
- Automate running multiple code batches overnight without manual intervention.
- Generate test suites across different code modules in parallel batches.
- Process large refactoring tasks by breaking them into autonomous development jobs.
Enables asynchronous development workflows where coding tasks progress without developer attention, reducing iteration cycles and freeing engineers to focus on architecture and review rather than repetitive implementation work.
Development teams using Claude Code seeking to parallelize multiple feature branches or refactoring tasks simultaneously.
https://github.com/aigorahub/elves
By aigorahub
How to Get It
git clone https://github.com/aigorahub/elves.git /tmp/elves && python3 /tmp/elves/scripts/sync_installed_skills.py --apply --target claude && rm -rf /tmp/elves
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me automate running multiple code batches overnight without manual intervention
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 171 GitHub stars; contributors unknown; last commit 1d ago; license MIT.
Things to check
- The author describes it as early scaffolding, not a finished product — it may not work out of the box, since your model, stack, test infrastructure, and review setup will differ. Skipping the two-step stage-then-launch flow is the most common cause of stalled runs. Requires Python 3 for the install script and git/GitHub PRs/CI for the workflow.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 171 GitHub stars; contributors unknown; last commit 1d ago; license MIT.