#290290th of 455 in Skills, plugins and prompts
open-steps
Plain-language report and question skills for Claude Code, Codex, Cursor and Gemini CLI
- Stars
- 1.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Shell
26 on 26 Aug 20261,281 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Eight agent skills that make coding agents report in plain words for non-engineers: a one-screen done-or-not verdict, numbered steps for the user's part, simple questions with a recommendation, and a BIG-PICTURE.md status file. Installs as a Claude Code plugin or by copying skill folders to ~/.agents/skills/, plus a routing block and two shell hooks. Skills can also merge PRs with green checks and an approved review.
Who it is for: Non-engineer builders using coding agents who want plain-language status reports
Strengths
- Works on Claude Code, Codex CLI, Cursor CLI and Gemini CLI from the same skill folders
- Activation measured: 25 phrases x 3 runs, 100% on Sonnet 5.5 and Opus 5.5, 0/9 off-topic
- Hooks and scripts are plain shell, and scoring uses a script rather than an AI judge
- Reports are stored outside repos in ~/.claude/open-steps/reports, so they stay out of commits
Weaknesses
- Haiku 4.5 activation is weaker: os-step-by-step fired 3/9 and os-say-simple 7/9
- Routing block and, on non-Claude tools, hooks must be wired by hand
- Skills can run gh pr merge; on Claude Code this is pre-approved without a prompt
- Permission handling and removal steps on Codex, Cursor and Gemini CLI are untested or doc-based
What it needs
- no GPU
- Needs git, gh (optional)
- Models: Claude Haiku 4.5, Claude Sonnet 5.5, Claude Opus 5.5, Codex CLI, Cursor CLI
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |