Shipwright — Agent Model
How autonomous engineering work gets planned, executed, reviewed, and shipped. Two input sources feed a coordination layer that drives a per-agent execution loop.
Ad hoc, human-triggered.
No cron — runs when you ask.
Per-repo, scheduled. Each cron feeds tasks to the task store.
ready task. Opens a PR.
Stages or posts findings.
Loops back until approved.
CI-green PRs.
Decomposes a feature or initiative into a task queue. Human-triggered — no cron. The human reviews the plan before tasks are queued into the task store. Human in the loop.
Scans for deviations from golden principles. Opens targeted refactoring PRs — one per principle. Most merge in under a minute. Human taste encoded once, enforced continuously.
Reads the diff, identifies stale sections, rewrites them in place. Commits as a separate docs commit. Prevents documentation debt from degrading agent performance over time.
Inventories the test system, identifies coverage gaps, flags slow or redundant tests. Queues tasks: add coverage at the right layer, remove tests superseded by better ones.
Reviews open Dependabot PRs. Approves safe patches, flags breaking changes, adds release-notes context. Reduces the review queue without requiring human attention on routine updates.
Large migrations broken into daily increments. Deprecate an endpoint, write a skill for the pattern, then let the loop chip away — one usage at a time until the codebase is clean. Each change is small, easy to review, and easy to roll back.
The coordination layer between task sources and executing agents. Owns task state, prevents duplicate work, tracks which agent owns what. Receives from planning and maintenance crons; feeds the core loop.
Picks up the next ready task from the task store. Explores the codebase, implements, opens a PR. Runs on a per-agent cron. The workhorse.
Reviews open PRs from any agent. Stages findings or posts inline comments. Enforces policy: blocking vs. advisory thresholds, auto-approve criteria. Agent-to-agent review — human override always available.
Addresses unresolved review findings on open PRs. Fixes blocking issues, pushes to the branch, and triggers re-review. The PR loops through review and patch until all findings are resolved.
Merges PRs that are approved and CI-green. Human override always available.
Captures corrections and cross-session patterns from the core loop. Routes improvements to CLAUDE.md and skills so the agent gets smarter with every cycle. Powered by learning loop (inline capture) and dreaming (async transcript mining).