From evanflow
Executes written implementation plans task-by-task with inline verification, TDD via evanflow-tdd, typechecks, lints, and tests. Stops on blockers. Use when a plan exists.
npx claudepluginhub evanklem/evanflow --plugin evanflowThis skill uses the workspace's default tool permissions.
See `evanflow` meta-skill. Key terms: **vertical slice**, **behavior through public interface**.
Executes written implementation plans: loads and critically reviews them, runs tasks in dependency order with parallel dispatch, separate worker-validator subagents, and verifies completion.
Executes written implementation plans using fresh subagents per task with TDD cycles, mandatory code reviews, and quality gates before proceeding.
Executes written implementation plans: loads and reviews critically, processes task batches with verifications, reports for feedback, iterates, completes via sub-skill.
Share bugs, ideas, or general feedback.
See evanflow meta-skill. Key terms: vertical slice, behavior through public interface.
docs/plans/... or wherever the user put it)Before doing anything else, scan the plan: does it have 3+ truly independent units that share a common interface contract?
If YES — offer evanflow-coder-overseer to the user before starting sequential execution:
"This plan has [N] independent units. We can execute sequentially or via
evanflow-coder-overseer(parallel coders + per-coder overseers + integration overseer + executable cohesion contract via named integration tests). Parallel is faster and adds independent QA. Which path?"
If the user picks coder-overseer, hand off there and stop this skill. If the user picks sequential — or if the plan doesn't qualify (tightly sequential dependencies, fewer than 3 units, no shared contract) — proceed to step 1.
For each task:
in_progressevanflow-tdd (skip only when plan flags an exception)tsc --noEmit, pnpm typecheck, cargo check, go vet ./...)eslint ., pnpm lint, cargo clippy, ruff check .)pnpm test, pytest, cargo test, go test ./...)completedStop immediately when:
Don't force through. Surface the blocker and ask. If the plan needs revision, return to evanflow-writing-plans.
After all tasks pass quality checks, hand off to evanflow-iterate for the self-review loop. Iterate finds issues a single pass missed (dead code, naming, scope creep, missing tests). For UI changes, iterate also views the rendered page.
When iterate converges: report what was done and STOP. Do NOT stage files (git add), do NOT commit, do NOT push, do NOT propose integration. The user decides every step from here.
A good "done" report includes: what files changed (one line each), what behaviors were added/changed, what verifications passed. Then await user direction.
evanflow-iterate (self-review loop) → report and STOPevanflow-writing-plansevanflow-coder-overseer (parallel coders + per-coder overseers + integration overseer)