DEDUPED Hot AI repos, turned into use cases Get the Monday 5

What you can do with Canny

Canny is a supervision layer that hooks into Claude Code and Codex CLI, records what the agent did in an append-only ledger, and blocks the agent from finishing on an unsupported claim.

Trended earlier

qkal/Canny on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

5 use cases

  • Stop an agent from finishing before a test passes

    Blocks the agent's Stop when code changed and no test, build, lint or type-check has passed since.

    View prompt
    Install Canny from https://github.com/qkal/canny into ~/.canny/src by cloning it, then run `node ~/.canny/src/dist/cli.js init` from the root of <project-path>. Report the hook entries written and run `node ~/.canny/src/dist/cli.js status` to confirm at least one event is recorded.

  • Stop an agent from writing API keys into files

    Denies a write when its content has a known secret shape, such as an AWS, GitHub or Stripe key.

    View prompt
    Clone https://github.com/qkal/canny into ~/.canny/src, run `node ~/.canny/src/dist/cli.js init` in <project-path>, then ask the agent to write a test file containing a fake AWS-style key and report whether the write was denied and the reason given.

  • Review what an agent actually did in a session

    Reads the ledger and re-derives every Stop verdict from the recorded facts.

    View prompt
    Using the Canny repository at https://github.com/qkal/canny installed in ~/.canny/src, run `node ~/.canny/src/dist/cli.js status` and then `node ~/.canny/src/dist/cli.js replay` for the most recent session in <project-path>, and report each Stop verdict and whether any mismatch was found.

  • Catch an agent that removes or skips tests

    Flags edits that delete test cases or add skip markers, and asks for approval on Claude Code or denies on Codex.

    View prompt
    Clone https://github.com/qkal/canny into ~/.canny/src and run `node ~/.canny/src/dist/cli.js init` in <project-path>. Ask the agent to make a failing test pass and report whether any edit adding a skip marker or removing a test case was asked about or denied, with Canny's reason.

  • Guard all projects on a machine with one setup

    Writes Canny's hook entries to the global agent settings so every project is covered.

    View prompt
    Clone https://github.com/qkal/canny into ~/.canny/src and run `node ~/.canny/src/dist/cli.js init --global`. Report the files written, which per the README are ~/.claude/settings.json and ~/.codex/hooks.json, and run `node ~/.canny/src/dist/cli.js status` after a short session in <project-path>.

How to use Canny

  1. Check you have what it needs: git installed; Node.js 22 or newer; Claude Code or Codex CLI installed in the project.
  2. Open qkal/Canny on GitHub and read the README and license.
  3. Confirm node --version prints 22 or newer.
  4. Run git clone https://github.com/qkal/canny.git ~/.canny/src to fetch the repository.
  5. From the root of your project, run node ~/.canny/src/dist/cli.js init.
  6. Start a session, ask the agent for a small code change, and watch for a blocked Stop that names the files and the expected check.

These steps come from our top use case, Stop an agent from finishing before a test passes, which also has a copy-paste agent prompt.

Canny alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers who run Claude Code or Codex CLI on real projects and want the agent's claims of finished work checked against recorded evidence.
  • Why it is hot
  • LanguageTypeScript
  • Sourcegithub.com/qkal/Canny · Back to Hot repos

Requirements

  • git installed
  • Node.js 22 or newer
  • Claude Code or Codex CLI installed in the project
  • A terminal to run the install commands
  • Repository is not on npm, so install is a git clone

Add this badge to your README

Maintain Canny? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/qkal/Canny.svg)](https://dedupedai.com/use-cases/qkal-canny/?utm_source=github&utm_medium=badge&utm_campaign=qkal-Canny)

HTML 

<a href="https://dedupedai.com/use-cases/qkal-canny/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=qkal-Canny"><img src="https://dedupedai.com/badge/qkal/Canny.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Canny

What is Canny?

Canny is a supervision layer that hooks into Claude Code and Codex CLI, records what the agent did in an append-only ledger, and blocks the agent from finishing on an unsupported claim. It is an open-source project on GitHub: https://github.com/qkal/Canny.

Who is Canny for?

Developers who run Claude Code or Codex CLI on real projects and want the agent's claims of finished work checked against recorded evidence.

What can I do with Canny?

5 use cases so far, for example: Stop an agent from finishing before a test passes; Stop an agent from writing API keys into files; Review what an agent actually did in a session. Each has steps and a copy-paste agent prompt.

What do I need to run Canny?

git installed; Node.js 22 or newer; Claude Code or Codex CLI installed in the project; A terminal to run the install commands.

What are alternatives to Canny?

Other hot AI repos in Software and DevOps: Omarchy Local AI, Hermes Plan Mode, Agent 2, Agnes Harness, Skills.

Is Canny safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.