Browse all 9 articles in this open-source series. Nine source-backed chapters on conditional guidance, live type contracts, loop design, iteration routing, review capacity and explicit authority.
Featured starting point
Understand the five skills, their different modification scopes and why the collection is not a ready-made autonomous maintenance service.
Suggested learning path
01 → 09
Understand the five skills, their different modification scopes and why the collection is not a ready-made autonomous maintenance service.
Evaluate a proposed CLAUDE.md rewrite using synthetic input, preserved commands and explicit safety constraints before changing future agent guidance.
Separate installing a skill from implementing a loop, review template assumptions and use GitHub’s actual workflow_dispatch prerequisites.
Map the set point, sensor, controller and actuator, then examine where persistent feedback actually enters the documented workflow.
Trace the workflow preflight and Bun prompt helper while distinguishing a routing marker from authentication and commentary from trusted instructions.
Measure accepted improvements, open-PR age, retries and human effort before increasing the cadence or batch size of a maintenance agent.
Review persistent guidance and CI credentials as consequential changes, not harmless text, and preserve task scope through iteration and recovery.
Decide when instruction cleanup, live-call-site type analysis or a recurring agent loop is appropriate, without treating automation as the default.
Model review capacity, exact iteration commands and missing policy without creating PRs or granting a learning prototype real write access.
