{
  "$type": "site.standard.document",
  "description": "The Ralph loop wraps your coding agent in an external while loop — fresh context each iteration, state externalized, the agent keeps going until the",
  "path": "/a-lighter-way-to-review-and-fix-your-coding-agent-s-work/",
  "publishedAt": "2026-02-15T05:23:00.000Z",
  "site": "at://did:plc:bryys25pc2fnagnyxqgsglhd/site.standard.publication/3mn26bjkkmh23",
  "tags": [
    "AI",
    "Tools"
  ],
  "textContent": "The Ralph loop wraps your coding agent in an external while loop — fresh context each iteration, state externalized, the agent keeps going until the feature is done. It's great for fire-and-forget tasks where you walk away and come back to a finished feature.\n\nBut sometimes I don't need all that. I'm in an interactive session, working with the agent, and I just want it to clean up what it's done before I commit. I don't need a fresh context or externalized state — I just need a quick review-fix cycle within my current session.\n\nTHE REVIEW+FIX SKILL\n\nI wrote about this briefly in my post on using a second LLM to review your coding agent's work. Here's the skill:\n\n---\nname: review-plus-fix-relentlessly\ndescription: Review dirty code and fix iteratively.\n  When user say to \"loop to fix dirty\" or \"review+fix\"\n---\n\nAll dirty repo changes are likely made in this session,\nthough not always\n\nUse the review dirty skill to review changes and fix\nto your best ability and matching repo preferences and\nstyle.\n\nAfter fixing, run review-plus-fix-relentlessly again,\nand before each cycle report how many cycles of\nreview+fix we have done.\n\nStop if code review skill doesn't not produce any more\nthings to fix\n\nIt calls my review-dirty skill which shells out to Codex for a fresh pair of eyes, then fixes whatever Codex flags, and loops. It stops when Codex has nothing left to complain about — usually 2-3 cycles.\n\nWHY NOT JUST USE A RALPH LOOP?\n\nA Ralph loop is designed for autonomous, long-running tasks. It externalizes state to files, spawns fresh agent sessions, and manages its own progress. That's overkill when I'm already mid-conversation with the agent and I just want it to tighten up its work.\n\nWith review+fix, I say two words and the agent loops — review, fix, review again — within my current session. No external scripts, no state files, no new processes. The context is already loaded. It knows what I asked for, what it changed, and why. It just needs a second opinion from Codex.\n\nWHEN I USE THIS\n\nAfter the agent implements something, I say \"review+fix\" and let it run for a minute. When I come back, the diff is cleaner than what I'd get from a single pass. I don't have to set up an external loop or hand off the whole task — I'm already in the session, so I just let it iterate.\n\nI also sometimes use review+fix as part of a bigger \"take over\" skill that lets the agent finish the task for me — review+fix, commit, deploy, all in sequence.",
  "title": "A Lighter Way to Review and Fix Your Coding Agent's Work"
}