Implement

Implement

Standard implementation flow: load style rules, make the change, run post-implementation QA.

Task Tracking

At the start, use update_plan to track each step, restating any remaining steps of a parent workflow alongside them:

1. Run $code-style skill
2. Load task-specific skills
3. Make the change
4. Run verification
5. Run $smoke-test skill for UI/UX changes
6. Run $preview skill for UI/UX changes
7. Post-implementation QA

Workflow state lives at .turbo/workflows/<slug>.md — slug from the governing plan when one is in context, otherwise the current branch name with non-alphanumerics replaced by hyphens. It pairs one-to-one with the thread's goal. When this run's create_goal attempt succeeds, write the file fresh: Status: active plus this invocation's update_plan list as a checkbox list. When an unfinished goal already exists, mirror into the workflow file its objective names; when it names none, continue without workflow state. Mirror every update_plan call into the file; it holds the pipeline's remaining steps and their statuses. When this run created the goal, run the terminal step in order: mark the final entry completed and mirror it, set Status: closed, mark the goal complete with update_goal, then emit any halt message.

Then attempt create_goal with the objective: "Make this change: <one-line task summary>. Carry it through Step 7, which runs $finalize unless a quick close or stopping is chosen. Workflow state: .turbo/workflows/<slug>.md; mirror every update_plan call into it. Loop state lives under .turbo/loops/. After any context compaction, re-read the workflow file and any active ledger, and continue from the first unfinished entry. Mark this goal complete when Step 7 has finished." If an unfinished goal already exists, an outer workflow owns it; continue without creating one.

Step 1: Run $code-style Skill

Run the $code-style skill to load existence, reuse, mirror, and symmetry rules before editing.

Step 2: Load Task-Specific Skills

Scan the work for types that match available skills, matching against the richest context available: a plan's Implementation Steps if a plan is in conversation context, otherwise the user request, a prior skill's task description, or an improvement entry. For each unambiguous match, run the skill by reading and following the installed skill instructions. For example, if the work includes "add a Drizzle migration" and a skill exists whose triggers reference Drizzle migrations, load it. If a work type has no matching skill trigger, do not load a generic skill.

If unsure, do not load.

Step 3: Make the Change

Apply the change described by the current context — the user request, a prior skill's task description, or an improvement entry. Keep the edit scoped to what the context describes.

When the fix changes how a value is constructed, grep for every other site that constructs it and fix the ones carrying the same defect; treat these siblings as part of the same change. If the scope balloons beyond what the context specified, stop and confirm scope before continuing.

Step 4: Run Verification

Before this step starts or uses a process that runs until it is stopped, such as a server or a watcher, run the $test-run-rules skill. Its rules verify without modifying code, so act on a failed check as this step directs.

If a Verification section is in conversation context (e.g., from a plan file), execute the commands, smoke checks, or MCP tool invocations it specifies. If a check fails, run the $investigate skill. If a check is blocked by a dependency, unclear requirement, or environmental issue, use request_user_input to surface the blocker and let the user choose how to proceed. If no Verification section is in context, go straight to the configuration check below.

When the Verification section lists both checks that can force code edits, such as a formatter or a linter, and a slow run, such as an integration suite, finish the edit-forcing checks and the edits they force before starting the slow run. When an edit lands after a slow run started, re-run it; when re-running is not practical in this session, state which part of the verification the final code did not get.

When the change adds or documents a configuration override — an environment variable, build flag, or any setting a reader is told to set — prove that a supported path delivers it: set the value, run the build or process meant to consume it, and confirm the output changed. When no supported path delivers it, fix the path or drop the documentation before this step completes. Restore the setting afterwards, and rebuild or discard any output produced with the non-default value. Passing checks are no evidence here, since a default that matches the value already in use keeps a broken override invisible to every run that never asks for a different one.