RocketLauncher / Claude Code

Claude Code Bucles

Flujos de trabajo de agentes que se repiten, como un bucle de revisión adversarial. 18 entradas.

18 de 18 componentes

  • adversarial-review-loop

    engineering

    Has a second, independent model review every change before merge so two different reviewers must agree, code only lands when both clear the bar.

  • anti-spin-build-loop

    engineering

    Builds toward a machine-checkable contract with explicit anti-spin guardrails, stops on no progress, repeated approaches, flip-flopping, or a spend budget.

  • build-test-fix-loop

    engineering

    Builds the next item on the plan, then runs tests, typecheck and lint, feeding every failure back as the next instruction until the build is green.

  • builder-reviewer-loop

    engineering

    Passes code between a builder and an independent reviewer subagent until the review has no blocking findings and tests pass.

  • completion-contract-loop

    engineering

    Writes a contract of what "done" means and what evidence proves each requirement before any work starts, then refuses to claim success without that evidence.

  • devils-advocate-loop

    evaluation

    Adversarially challenges a design or decision until every serious objection is resolved or explicitly accepted.

  • docs-sweep-loop

    engineering

    Keeps documentation aligned with the current codebase and opens a reviewable pull request on every pass.

  • five-minute-maintainer-loop

    engineering

    Every few minutes while you work, makes one small verified repository improvement, a flaky test, a stale comment, a missing type, one change, one commit.

  • goal-refiner-loop

    engineering

    Rewrites a vague request into a precise goal, exact end state, how to verify it, what not to touch, and the stop condition, then executes against it.

  • human-approval-loop

    evaluation

    Runs the task, then pauses and sends you approve / revise / skip before anything ships, human review as a first-class queue where the stop condition is your approval.

  • nightly-changelog-loop

    operations

    Updates the changelog every night with user-relevant changes and notifies the team when it ships.

  • overnight-pr-routine-loop

    operations

    A nightly routine that watches your open PRs, auto-fixes build failures, answers review comments in a fresh worktree, and rebases stale branches while you sleep.

  • perf-budget-loop

    engineering

    Profiles and optimizes the app pass after pass until it consistently meets a defined performance budget.

  • production-error-sweep-loop

    engineering

    Triages production errors, finds the root cause, ships a verified fix, and repeats until the error budget is clean.

  • quality-streak-loop

    evaluation

    Runs realistic scenarios and fixes failures until the suite passes N times in a row with no regressions.

  • repo-cleanup-loop

    engineering

    Recovers valuable unmerged work and prunes stale branches and PRs until the repository is tidy.

  • test-coverage-loop

    engineering

    Adds meaningful tests pass after pass until the suite reaches a target coverage threshold and stays green.

  • ticket-to-pr-loop

    engineering

    Converts open bug reports and issues into verified, reviewer-ready pull requests, one ticket per pass.

Incluye componentes de código abierto. Copyright (c) 2026 RocketLauncher AI and contributors. Licencia MIT.