Guardrails Learning Loop
Automation
by loops! by elorm
When a check fails twice the same way, append a guardrail sign to .ralph/guardrails.md so the next iteration avoids repeating it.
Prompt
Step 1 — Read guardrails Read .ralph/guardrails.md before any work. Treat each sign as a hard constraint. Step 2 — Run checks Run the project's backpressure commands. Check: `npm test && npm run lint` Step 3 — Record failure sign If the same error occurred before, append a concise sign to guardrails.md: what failed and how to avoid it. Step 4 — Fix with guardrails Apply a fix that respects all guardrail signs. Do not repeat prior failed approaches. Step 5 — Repeat until done Repeat the steps above until: Checks pass and no repeated failure pattern remains Check with: `npm test && npm run lint` Stop after 12 iterations and report what is blocking.
Platforms
CHATGPTCLAUDE
CHATGPTCLAUDE
Use this prompt in AIniverse
Tap to copy, run it on ChatGPT / Claude / Gemini, save to your stack, or remix.
Open in AppMore Automation prompts
Security Audit Weekly
Weekly npm audit scan, triage vulnerabilities by severity, and propose or apply safe patches.
Knip Until Clean
Find and remove dead exports, unused files, and orphan dependencies — loop until knip reports clean.
Ship PR Until Green
Implement on a branch, run tests, push, open a PR, wait for CI, and loop until checks pass and the PR is ready to merge.
Ralph Story Executor
Fresh-context loop: pick one incomplete story from prd.json, implement it, run backpressure checks, commit, and updat...