Polish Code

Polish Code

Task Tracking

At the start of every invocation (including re-runs from Step 7), use update_plan to track each step, restating any remaining steps of a parent workflow alongside them:

1. Run $stage skill
2. Deterministic cleanup
3. Run $review-code skill
4. Run $evaluate-findings skill
5. Run $apply-findings skill
6. Run $smoke-test skill
7. Re-run $polish-code skill if changed

Loop State

Loop state lives at .turbo/loops/<slug>.md — slug from the governing plan when one is in context, otherwise the current branch name with non-alphanumerics replaced by hyphens. At the start of every invocation, read the ledger if it exists.

• Fresh loop (no ledger, or its Status: line is closed): write a fresh ledger with Status: active, then attempt create_goal with the objective: "Run the $polish-code loop on until converged: a run with no changes, an in-place-only round, or remaining findings that do not justify another re-run. Loop state: .turbo/loops/<slug>.md; re-read it after any context compaction and do not re-adjudicate findings it records as rejected. Mark this goal complete when the loop converges." If an unfinished goal already exists, an outer workflow owns it; continue without creating one.
• Continuing loop (Status: active): this invocation is the iteration after the last one the ledger records, whether a Step 7 re-run or a resumption after an interruption. Continue from the recorded state. A Pending smoke-test baseline entry means a previous iteration was interrupted between delegating the smoke test and verifying the tree: reconcile the tree against that entry and clear it before Step 1, so Step 1 does not stage what the interrupted sub-agent left behind. If no unfinished goal exists, attempt create_goal with the same objective as a fresh loop.
• During each iteration: have the ledger path in context when Steps 3 and 4 run so recorded verdicts are honored. After Step 7's classification, append the iteration number, the round's applied, rejected, and escalated verdicts with reasons, and the classification.
• Convergence stop (a run with no changes, an in-place-only round, or a further re-run judged pointless): set Status: closed; if this loop created the goal, mark it complete with update_goal. An inherited goal stays active for the outer workflow. A halt on an unresolved failure leaves Status: active and the goal untouched, so the next invocation resumes the recorded state.

Step 1: Run $stage Skill

Run the $stage skill.

Step 2: Deterministic Cleanup

Run the project's full verification gate: every check it defines as a pass/fail condition. The goal is that passing this step means the project's own checks (and CI, where it exists) pass. Build the gate by combining every source below that the project declares (sources 1-3); run the baseline (source 4) only when the project declares none of them:

1. CI config — where present, it is the authoritative gate; run the checks it enforces.
2. Check scripts — package-manager scripts (check, verify, lint, typecheck), Makefile or Taskfile targets, or a combined format+lint script.
3. Configured tools — any tool with a config committed to the repo, such as a dead-code or unused-dependency gate. A committed config means the project treats the tool as a gate; run it even when no script or CI invokes it. Do not run such a tool when the project has not configured it; unconfigured runs are discovery, which belongs to $find-dead-code.
4. Baseline — when the project declares nothing more, run the formatter, then the linter, then the test suite.

Run the formatter first so later checks see formatted code, then the rest. Fix any failure the tools do not auto-resolve. For test failures, run the $investigate skill to diagnose the root cause, apply the suggested fix, and re-run; if investigation finds no root cause, stop and report with its findings.

Stage all changes made in this step before continuing.