mcpField
R
re0-loop

re0-loop

github.com/lilmgeniusAgent workflows1.4k1.2k installsUpdated 4w ago
Repository

About re0-loop

re0-loop is an agent skill for running iterative project cycles from framing and building through real-surface checks and reflection. It emphasizes quality-gated reusable work, explicit next steps, and preserving lessons between cycles.

Key features

  1. 01Frame work and define quality gates
  2. 02Build a complete vertical slice
  3. 03Validate through the real surface
  4. 04Extract lessons and anti-patterns
  5. 05Choose whether to iterate or restart
  6. 06Version only quality-cleared work

Use cases

  1. 01Develop a project through evidence-backed cycles
  2. 02Test a web, API, desktop, or CLI artifact
  3. 03Carry anti-patterns into the next development pass

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lilmgenius/paperthin --skill re0-loop

After installing, type/re0-loopin Claude Code to confirm it loaded.

Details

From the project README

Run the cycle so learning compounds and code accumulation does not masquerade as progress.

Goal

re0-loop keeps a project moving through repeated turns:

FRAME -> BUILD -> DRIVE -> RE0-MEMO -> HATE -> RE0-WORK -> BUILD AGAIN

The unit of progress is not hours, files, panels, or features. It is the count of quality-cleared templates, reusable platform modules, and anti-patterns eliminated in later cycles.

Workflow

  1. Frame the thesis and quality gates.
  2. Build one complete vertical slice.
  3. Drive it through the real surface: browser for web apps, HTTP for API contracts, computer-use for desktop apps, and CLI only for data-shaped artifacts.
  4. Run re0-memo to extract lessons, anti-patterns, and next-cycle gates.
  5. Decide whether the next pass iterates in place or uses re0-work; when that call or the next move is unclear, nba reads the cycle state and returns the single next action.
  6. Kill the next plan before build: use the project's adversarial review skill or a human-invoked attack when that skill is user-only.
  7. Version only templates or modules that clear their gates.

Rules

  • Tests are supporting evidence, not the gate; every turn needs a real-surface proof sized to the artifact.
  • Do not widen before the core loop clears.
  • Do not confuse generated variety with structural variety. If many outputs converge to the same shape, the cycle failed the variety gate.
  • Preserve negative corpus so later cycles can prove the same anti-pattern is gone.
  • Let code die. A restart that preserves the right lessons is progress.
  • Stop a lap when no outside truth enters; add evidence before another internal pass.

Verification

Before finishing a lap:

  1. The real surface was driven and evidence was captured.
  2. The re0-memo names at least one lesson, anti-pattern, or gate that affects the next pass.
  3. The keep/iterate/re0-work decision is explicit.
  4. Any version label belongs only to a quality-cleared template or module.

Comments

Markdown supported