Refine Plan

Loop the review pipeline over a plan until no new findings are accepted. Writes back to the plan file in place.

Task Tracking

At the start of every invocation (including re-runs from Step 5), use TaskCreate to create a task for each step:

1. Resolve the plan
2. Run /review-plan skill
3. Run /evaluate-findings skill
4. Run /apply-findings skill
5. Re-run /refine-plan skill if changed

Step 1: Resolve the Plan

1. Explicit path — use it
2. Explicit slug — resolve to .turbo/plans/<slug>.md
3. Single file — Glob .turbo/plans/*.md. If exactly one file exists, use it
4. Most recent — most recently modified file
5. Legacy fallback — .turbo/plan.md if .turbo/plans/ does not exist
6. Nothing found — tell the user to run /turboplan and stop

If multiple candidates exist and the choice is non-obvious, use AskUserQuestion.

State the resolved path before continuing.

Unless an explicit path or slug was passed, confirm the resolved plan still describes work that remains to be done. The signal is a frontmatter status: of done.

When the signal fires, output it as text. Then use AskUserQuestion to offer:

• Refine anyway — the marker is stale
• Pick another plan — resolve to a different file under .turbo/plans/, then confirm that plan against this same signal
• Leave the plan alone — skip refining

On Leave the plan alone, mark the remaining refine steps deleted, then use the TaskList tool and proceed to any remaining task.

Step 2: Run /review-plan Skill

Run the /review-plan skill on the resolved plan.

Always run this step even if the plan looks polished.

Step 3: Run /evaluate-findings Skill

Run the /evaluate-findings skill on the review findings from Step 2.

Step 4: Run /apply-findings Skill

Run the /apply-findings skill on the evaluated results.

Step 5: Re-run /refine-plan Skill if Changed

Check whether the plan file was edited during Step 4. Any edit counts.

The iteration number below refers to the /refine-plan run currently executing Step 5. It is not the iteration number of a prospective re-run. Iteration 1 is the initial run; iteration 2 is the first auto-re-run; iteration 3 is the second auto-re-run; iteration 4 and beyond exist only when the user opts in at the hard-cap ask. Iterations 1 and 2 always follow the classification gate (they never trigger the hard cap at their own Step 5, even when the auto-re-run they spawn would be iteration 3). The hard cap fires at the end of iteration 3 and every iteration thereafter.

Iterations 1 and 2, if changes were made, classify what Step 4 edited:

• Structural edits — run /refine-plan again via the Skill tool, passing the resolved path. If the round contains both structural and prose-only edits, treat it as structural and re-run automatically.
• Prose-only edits only (reworded sentences in place, fixed stale examples, clarified existing text without changing meaning) — output a summary of what changed, then use AskUserQuestion to ask whether to run one more round or stop here. Do not silently continue or silently stop.

Iterations 1 and 2, if changes were made but you believe re-running is unnecessary, use AskUserQuestion to ask for skip permission. Do not skip silently.

Judge whether another round is worthwhile by the trend across iterations: when rounds have stopped surfacing defects (contradictions, infeasible steps, missing requirements) and keep surfacing improvements of kinds earlier rounds already applied, the loop has converged even though the edits were structural — recommend stopping. A round that surfaces no defects is the termination signal; never add a confirmation round, an extra reviewer, or review steps beyond this skill's own.

Judge the kind of surviving defect as well as the trend. Once earlier rounds have drained the design- and requirement-level defects and a round's findings are dominated by claims that a named identifier does not exist or does not match its declaration, the plan has passed the point where reviewing it as text pays, even when the count is rising and every finding is genuine. Implementation surfaces that class immediately, so recommend stopping. Expect any round that adds mechanism to seed defects at the seams it creates.

When a round's findings turn on behavior nobody has observed, either how a platform, framework, or dependency behaves, or what a plan-specified algorithm produces on its inputs, prefer a cheap instrumented experiment to another review round. Run it in a temp directory outside the repo, and record what it shows in the plan before judging whether another round is warranted. For a plan-specified algorithm, write it as a script there, assert the plan's stated postconditions over randomized and degenerate inputs, and rewrite its rule only from what that run shows. Keep in the sample the inputs on which a postcondition is hard or impossible to meet, and judge each of their outcomes against that postcondition. When only a person's real input can show the behavior, such as keyboard focus or a gesture, use AskUserQuestion to ask the user for a short hands-on check in place of the experiment, and record what they report the same way. Mark a behavior that could not be observed as unobserved.

Iteration 3 or later, if Step 4 of this run made changes, the hard cap is reached. This replaces the classification gate above for iteration 3 and every iteration after it. Output a summary of what is still changing and whether it is structural or prose-only. Then use AskUserQuestion to offer three options: run another iteration; stop iterating, accepting the plan as-is so the workflow moves on; or escalate to /consult-oracle for a different perspective on the remaining issues.

Before acting on any gate above, check for a context signal. Call the mcp__context-level__read tool: a reading of 25% or less remaining is one. A request from the user to compact, arriving since the session last compacted, is the other. When either is present, turn whatever this step reached, including an automatic re-run and a run that left the plan unchanged, into one AskUserQuestion call. Its first question asks whether to compact before what comes next: "Handoff, then compact", marked recommended, or keep going in this session, which acts on the gate's answer here. Leave it out when the user asked to compact. Its second question offers the choices of the gate this step reached, with the recommendation that gate would make; in place of an automatic re-run, it offers run another iteration, marked recommended, or stop iterating. Leave it out when Step 4 left the plan unchanged. Make no AskUserQuestion call when both are left out. When the plan is unchanged and TaskList shows no pending task that no /refine-plan iteration created, nothing remains to resume: ignore the signal and let the loop end.

On "Handoff, then compact", or when the user asked to compact, check first whether the gate's answer is stop iterating while TaskList shows no pending task that no /refine-plan iteration created. Then nothing remains to resume: tell the user so and close this step without a handoff. Otherwise run the /create-handoff skill, or, when this session already wrote a handoff, edit that file. Point its next step at what the gate's answer leads to, and once the handoff is written, update this step's task as that branch says:

• Run another iteration — the re-run. The handoff carries the number of the iteration about to run, the already-adjudicated list this step supplies to it, and the resolved plan path. Use TaskUpdate to set this step's task description to the re-run: run /refine-plan on that path as that iteration, reading the already-adjudicated list from the handoff at its path. Leave the task in progress.
• Escalate to /consult-oracle — the escalation. The handoff carries the summary above and the same state as on another iteration. Use TaskUpdate to set this step's task description to that escalation, reading that state from the handoff at its path. Leave the task in progress.
• Stop iterating, or the plan is unchanged — the first pending task that no /refine-plan iteration created. Mark this step's task completed, along with every Step 5 task earlier iterations left in progress.

Then end the turn in place of the TaskList call that closes this step, telling the user to run /compact and then reply "continue".

When the same class of defect recurs across iterations, stop patching the individual instance and instead write the root-cause invariant into the plan itself, enumerating the worked failures it must prevent. Count a defect that swings to the opposite failure after its fix, such as a check found too strict in one round and too lax in the next, as the same class recurring. In the same pass, re-read the whole plan against the new invariant and fix every instance it catches, including text written before the invariant existed. Treat recurrence on a new axis of the same invariant as a signal that the invariant is incomplete: widen it to cover the new axis rather than assuming the latest fix failed. When the recurring defect turns on behavior nobody has observed, run that experiment, or ask for that hands-on check, before writing the invariant: an invariant derived from reasoning can be wrong in exactly the way the mechanism it replaces was wrong, and every later round is measured against it.

When successive rounds move away from each alternative in turn on a different ground and the loop arrives back at a design an earlier round left behind, treat that as evidence the first finding's severity was misjudged against the alternatives' failure modes. Re-examine that finding rather than inventing another mechanism: when the earlier design survives the comparison, adopt it and record that finding as Skip, citing the alternatives' failure modes; when the user chose the direction that displaced it, surface it as Escalate, naming the original decision and this evidence beside it.

When a round has adopted a scope narrowing to limit blast radius, check that the narrowing is derivable. The narrow case is implementable only when the fact distinguishing it from the broad case is available to the implementation at the point the rule runs, whether from persisted state, the request, configuration, or data already at hand; when nothing supplies that fact, the two cases are indistinguishable at runtime and the rule silently strands whatever it excludes. Widen back to the broad case rather than carrying a rule nothing can evaluate, unless the user chose the narrowing: then surface it as Escalate, naming the original decision and this evidence beside it.

The re-invocation is a full, fresh run of this skill, always passing the resolved path. Every step (1-5) executes with its own task tracking and skill invocations. Whichever gate above sends the run into another iteration, supply that iteration with every Skip and Escalate verdict recorded so far, across this run and earlier iterations, as the already-adjudicated list for /review-plan, one line each: the finding, its verdict, and the recorded reason. Fresh task tracking leaves that list intact. A finding that re-proposes a design an earlier round left behind stays in scope regardless of the list: the alternatives having since failed on their own grounds is evidence the earlier reason did not account for, and it is the signal the rule above depends on.

Then use the TaskList tool and proceed to any remaining task.

Structural Edit Examples

Added or removed steps, new or removed design decisions, rewired dependencies between steps, changed acceptance criteria, changed the deployment's stated bounds, changed testing strategy.

Rules

• Every step must run in every iteration. /evaluate-findings is a judgment gate that must run before /apply-findings touches the plan. Each step must invoke its designated skill via the Skill tool.
• Re-invocations from Step 5 are full runs with fresh task tracking and complete skill invocations.
• The plan file is the only file that should change.