autopilot

Solid

Use when supervising a Smart Cascade run: bootstrap and verify Root, observe lifecycle/progress, intervene or recover on drift/stall/blockers, and verify/report run completion without becoming the production scheduler.

AI & Automation 3 stars 0 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Autopilot Autopilot is the external supervisor for one Smart Cascade run. Root is the sole production coordinator and owns the complete DAG, ready-frontier scheduling, Leader/Advisor coordination, slice decisions, commits, integration, and cleanup. Read before controlling a run: - [`references/architecture.md`](references/architecture.md) - [`references/run-contract.md`](references/run-contract.md) - [`references/state-machine.md`](references/state-machine.md) - [`references/queue-validation.md`](references/queue-validation.md) - [`references/state-validation.md`](references/state-validation.md) - [`references/digests.md`](references/digests.md) - [`references/acceptance-gates.md`](references/acceptance-gates.md) - [`references/hierarchical-lanes.md`](references/hierarchical-lanes.md) - [`references/smart-cascade-flow.md`](references/smart-cascade-flow.md) Supervision settings — which profile Root is initialized under, which verifier agent to start, observation interval, commit-dialog answer — live in [`autopilot-config.yaml`](autopilot-config.yaml). Read the effective values from there instead of hardcoding them, and change a default by editing that file. Precedence is an explicit user or frozen-run override, then that file, then the Skill default. Before any Herdr command, load the installed `herdr` skill and follow its current syntax and environment boundary. Herdr owns Root terminal transport and process observation. OMP owns native subagent communication and child...

Details

Author
shttty
Repository
shttty/smart-cascade
Created
4 months ago
Last Updated
4 days ago
Language
Python
License
MIT

Integrates with

Anthropic · AI

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

autopilot

Use for a large, open-ended mission that must survive sessions/crashes and run user-out-of-loop until STOP; delegates lifecycle work to other skills. Not for pre-scoped delivery that stops at a PR gate; use orchestrate's autonomous mode or deliver.

1 Updated yesterday
mblauberg
AI & Automation Listed

autopilot

Drive the whole plan end-to-end unattended by chaining start-phase, each chat's execute-batch (subagent-per-batch), and close-phase across one or more phases — with checkpoint/resume, fail-halt guardrails, model tiering, and a usage-governor seam; use when the operator invokes /tandem:autopilot or asks to run the plan autonomously, hands-free, or unattended.

0 Updated 1 weeks ago
DATA-AI-XYZ
AI & Automation Solid

autopilot

Self-improvement loop: each hourly run implements the oldest open issue labeled `autopilot` that has no open PR. When the queue is empty it runs first-principles `/audit harness` research, files its own `autopilot` ticket from the top-ranked finding, and builds that. Decomposes via the pm agent, then runs `/ship-spec --issue`, which owns the build end-to-end (the two compacts bracketing implement, a worktree Advisor, `/delegate` workers running `.oh/scripts/ralph.sh`, the `/eval` gate, and the `/audit pr` promotable undraft) through to a ready-for-review PR whose description states why this item was selected. Harness-infra only (skills/rules/docs/scripts/crons/wiki) — never sandbox application code. Runs in its own per-run tmux session. Caps: 6 open autopilot PRs created per UTC day AND 10 total open; never auto-merges. TRIGGER when: the hourly .oh/crons/autopilot.md fires, or invoked manually on demand (e.g. /autopilot --dry-run to preview the next selection).

38 Updated today
mifunedev