What do you want to do?
4 use cases
-
Get a one-screen done-or-not report after each session
Ask "are we done?" and get a verdict on done, needed input, new debt and whether it is safe to close.
View prompt
In the open-steps repo at <repo-path>, use the os-done-or-not skill to report on the work just finished for <task-name>. Expected output: a one-screen report with a Fully done row, an Anything needed from you row, a New debt row and a Safe to close row. Verify that each row states a verdict and does not rely on commit hashes alone.
-
Turn agent requests into numbered steps you can follow
When the agent needs you to run, paste, click or approve something, get exact numbered steps instead.
View prompt
In the open-steps repo at <repo-path>, use the os-step-by-step skill for the next action that needs a human on <project-name>. Expected output: numbered steps a non-technical person can follow, with only the actions that truly need the person listed. Verify that the agent tried every step it could do itself before asking.
-
Check another agent's "done" claims before accepting them
Verify each claim from another session against what actually happened, then get a next action.
View prompt
In the open-steps repo at <repo-path>, use the os-check-work skill to verify the claims in the report from <other-session> about pull request <number>. Expected output: each claim marked against what actually happened, followed by one recommended action. Verify that no claim is accepted without a check.
-
Keep a plain-language status file for the whole project
Maintain one BIG-PICTURE.md with every feature, its progress, unused parts and queued work.
View prompt
In the open-steps repo at <repo-path>, use the os-big-picture skill to update BIG-PICTURE.md for the project at <project-path>. Expected output: a plain-language file listing each feature with its progress, any unused parts and the queued work. Verify that no task was invented and nothing was deleted.
How to use Open Steps
- Check you have what it needs: git, to download and update the pack; One of Claude Code, Codex CLI, Cursor CLI or Gemini CLI installed; gh, GitHub's command-line tool (optional; without it some output says "not checked").
- Open kharmanskyi/open-steps on GitHub and read the README and license.
- Run
git clone https://github.com/kharmanskyi/open-steps.git - Run
claude plugin marketplace add ./open-steps && claude plugin install open-steps@open-steps(Claude Code) - Run
grep -q 'os-done-or-not' ~/.claude/CLAUDE.md 2>/dev/null || cat open-steps/docs/routing-block.md >> ~/.claude/CLAUDE.mdto add the routing block - Finish a unit of agent work and ask the agent "are we done?"
These steps come from our top use case, Get a one-screen done-or-not report after each session, which also has a copy-paste agent prompt.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeOpen Steps alternatives · Best AI repos for Software and DevOps
About this repo
- Who it is forBuilt for people who direct AI coding agents without an engineering background and need to know whether work is finished and what they must do next.
- Why it is hot
- LanguageShell
- Sourcegithub.com/kharmanskyi/open-steps · Back to Hot repos
Requirements
- git, to download and update the pack
- One of Claude Code, Codex CLI, Cursor CLI or Gemini CLI installed
- gh, GitHub's command-line tool (optional; without it some output says "not checked")
Maintain Open Steps? Add the Featured on Deduped badge
Paste this into your README:
[](https://dedupedai.com/use-cases/kharmanskyi-open-steps/?ref=badge)
Questions about Open Steps
What is Open Steps?
A set of plain-language agent skills for Claude Code, Codex CLI, Cursor CLI and Gemini CLI that turn agent work into honest reports, clear verdicts and steps a non-engineer can follow. It is an open-source project on GitHub: https://github.com/kharmanskyi/open-steps.
Who is Open Steps for?
Built for people who direct AI coding agents without an engineering background and need to know whether work is finished and what they must do next.
What can I do with Open Steps?
4 use cases so far, for example: Get a one-screen done-or-not report after each session; Turn agent requests into numbered steps you can follow; Check another agent's "done" claims before accepting them. Each has steps and a copy-paste agent prompt.
What do I need to run Open Steps?
git, to download and update the pack; One of Claude Code, Codex CLI, Cursor CLI or Gemini CLI installed; gh, GitHub's command-line tool (optional; without it some output says "not checked").
What are alternatives to Open Steps?
Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.
Is Open Steps 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.