Use Laizy as the control plane around existing coding agents, not as a replacement for them.
Create or refresh a local milestone plan file for the target repo.
IMPLEMENTATION_PLAN.md by convention.{baseDir}/references/planner-bootstrap.md.Bootstrap the run once with laizy start-run.
Use laizy supervisor-tick as the source of truth for every later decision.
Read the emitted bundle and follow the bounded next action instead of improvising the next step in chat.
Bootstrap a run:
bash
laizy start-run \
--goal "<user goal>" \
--plan IMPLEMENTATION_PLAN.md \
--out state/runs/<run-name>.json
Evaluate the next action:
bash
laizy supervisor-tick \
--snapshot state/runs/<run-name>.json \
--out-dir state/runs/<run-name>.supervisor
Read {baseDir}/references/decision-map.md for the full artifact map. The short version is:
plan / replan
planner.request document.needs-plan mode, re-run start-run after the planner lands the first actionable milestone queue.continue
recover
verify
closeout
Use the runtime profile emitted by Laizy when spawning planner, implementer, recovery, or verifier workers.
model, thinking, and reasoningMode when the platform allows them.Treat generated run artifacts as local state:
state/runs/ out of gitstate/verification/ out of git.tgz files out of git{baseDir}/references/decision-map.md for emitted artifact names and what to do for each supervisor decision.{baseDir}/references/planner-bootstrap.md when you need a clean planner-needed starting point for a new multi-step run.