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

How to switch off or rewrite rules that never fire or fire wrongly with Abide

Score each rule against your git history, disable the broken ones, and have the agent rewrite the rest.

Who it is forA developer who wrote a rubric from their instruction files and finds some rules either silent or noisy.

The problemA badly worded rule scores 0.4 on everything and never fires, so it adds no protection and nobody notices.

The outcomeRules that never fire are switched off, and remaining rules are reworded so their verdicts are useful.

What you need first

  • A TypeSafe API key from typesafe.ai, or a Vercel AI Gateway key
  • A terminal with npx available
  • A git repository with project instruction files such as AGENTS.md or CLAUDE.md
  • One or more supported agents installed: Claude Code, Codex, OpenCode or Pi

Steps

  1. Run abide report to see your rules, which ones fired, and which never fire.
  2. Run abide calibrate to score every rule against twenty real hunks from your git history.
  3. Run abide tune to have the agent rewrite the rules that never fire.
  4. Run abide compile to recompile the rubric now instead of waiting for the next session.
  5. Run abide report again and confirm the rules changed as expected.

Prompt for your agent

In the repo <repo-path>, run `abide report`, then `abide calibrate`, then `abide tune`. Report which rules were switched off or rewritten, and confirm `.abide/rubric.json` still parses.

Caveat. The README says compile and tune use Claude Code by default or Pi when Claude is unavailable, so one of those must be installed and logged in.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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