Back to directory

Governed Autonomy Loop

Agent skill
1 skill

Turn any work-queue + any enforcement pipeline into a self-driving, self-healing, human-minimal autonomy loop with a control-systems safety envelope. A prose-defined governor closes a feedback loop over the queue, drives isolated worktree arcs to Done, is metacognitive (defers when the runtime can't support the act, escalates only when genuinely blocked, self-heals when the block clears), and NEVER performs the irreversible act itself — it delegates every merge/deploy/publish to an isolated arc gated by adversarial review + a policy gate + a server-side aggregate check. The controller is a markdown prompt interpreted fresh each tick; a thin tested shell (tick.sh) only schedules, locks, and logs. The skill SCAFFOLDS + GOVERNS a new loop instance: the invariant spine stays fixed, four adapters (tracker / irreversible-act + enforcement / runtime / partition) are per-instance, the deterministic core (scheduler, in-flight fold, reseed gate, config + denylist validation) is extracted into tested scripts, and the latent decisions stay prose with scenario evals. Generalizes the proven broomva ticket-dispatch governor (BRO-1740 + BRO-1833). USE WHEN setting up an autonomous ticket/PR/deploy loop, standing up a governor that drives a queue unattended, building a self-merging arc pipeline, adding a metacognitive control loop over background agents, or the user says "governed autonomy loop", "autonomy loop", "self-driving loop", "ticket-dispatch governor", "loopcast", "loop-caster", "set up an autonomous governor". NOT FOR a single in-session autonomous task (use /autonomous), a one-shot background watcher (use P9 wait), or a cross-session single-agent restart loop with no queue (use P12 persist) — this is the external-trigger, across-session, queue-driven, irreversible-act-gated quadrant.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryGeneralStars0

About this skill

Turn any work-queue + any enforcement pipeline into a self-driving, self-healing, human-minimal autonomy loop with a control-systems safety envelope. A prose-defined governor closes a feedback loop over the queue, drives isolated worktree arcs to Done, is metacognitive (defers when the runtime can't support the act, escalates only when genuinely blocked, self-heals when the block clears), and NEVER performs the irreversible act itself — it delegates every merge/deploy/publish to an isolated arc gated by adversarial review + a policy gate + a server-side aggregate check. The controller is a markdown prompt interpreted fresh each tick; a thin tested shell (tick.sh) only schedules, locks, and logs. The skill SCAFFOLDS + GOVERNS a new loop instance: the invariant spine stays fixed, four adapters (tracker / irreversible-act + enforcement / runtime / partition) are per-instance, the deterministic core (scheduler, in-flight fold, reseed gate, config + denylist validation) is extracted into tested scripts, and the latent decisions stay prose with scenario evals. Generalizes the proven broomva ticket-dispatch governor (BRO-1740 + BRO-1833). USE WHEN setting up an autonomous ticket/PR/deploy loop, standing up a governor that drives a queue unattended, building a self-merging arc pipeline, adding a metacognitive control loop over background agents, or the user says "governed autonomy loop", "autonomy loop", "self-driving loop", "ticket-dispatch governor", "loopcast", "loop-caster", "set up an autonomous governor". NOT FOR a single in-session autonomous task (use /autonomous), a one-shot background watcher (use P9 wait), or a cross-session single-agent restart loop with no queue (use P12 persist) — this is the external-trigger, across-session, queue-driven, irreversible-act-gated quadrant.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 18cef9f304875c4e0e4ada4b5f2a657b6fc64a987f07f87abd6e4e5c1dd4b02f

About scan coverage and limitations

About this listing

Category
General
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.