DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to gate a solo refactor with a verified GATES.md ledger with Unlazy

Turn a substantial change into runnable gates and re-check them before claiming done.

Authorization notice. Unlazy is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Credentials. Checks run with ambient filesystem, environment, credential, and network access, so a gate command can touch secrets or external services.

Who it is forA developer or agent finishing a multi-step refactor who wants evidence, not a claim, that every outcome works.

The problemAgents often declare substantial work complete after a partial check, and nothing records which outcomes were actually verified.

The outcomeA GATES.md ledger where each outcome has a command and expected output, and a re-run that confirms every gate passes.

What you need first

  • Node.js 16 or newer
  • An AI agent that supports skills, such as Claude Code or Codex CLI
  • A repository with a task to verify and shell commands the gates can run

Steps

  1. Run npx skills add Leonxlnx/unlazy to install the skill.
  2. Copy templates/gates-leaf.md to GATES.md in the project root and replace every placeholder with a real outcome, CHECK command, and EXPECT string.
  3. Run node /scripts/gate-check.mjs --status GATES.md to inspect the ledger without executing any command. (inferred, check the README)
  4. Read every CHECK command and the scripts it calls, then run node /scripts/gate-check.mjs --approve GATES.md. (inferred, check the README)
  5. Run node /scripts/gate-check.mjs --reverify GATES.md and treat only a passing re-run as completion. (inferred, check the README)

Prompt for your agent

Use the unlazy skill in the repo <repo-path> to refactor <target-module>. Write GATES.md from templates/gates-leaf.md with one runnable gate per outcome, then run node /scripts/gate-check.mjs --reverify GATES.md. Report the gate results, and verify that every gate is marked met before you say the work is complete.

Caveat. The checker only proves the shell command you declare, so a weak CHECK line can pass while the outcome is still broken.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page