kharmanskyi/open-steps

Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.

8 skills listed · MIT · 1.3k stars · last pushed 5 Oct 2026

kharmanskyi/open-steps on GitHub

Across these 8 skills

Pattern check

Nothing flagged in 6

Items to review in 2: os-big-picture and os-what-could-go-wrong

What it can touch

8 pre-approve tools
6 run shell commands
2 bundle scripts
+2 more
- 1 reaches the network
- 1 runs commands as it loads

Checked at commit 4fa744b on 29 Oct 2026.

Install the collection

2 of these skills have items to review. Read them before you install the whole collection.

Claude Code plugin

Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add kharmanskyi/open-steps --scope user &&claude plugin install open-steps@open-steps --scope user

Any agent

Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add kharmanskyi/open-steps

Skills

All8 Items to review2

Skills in kharmanskyi/open-steps, page 1 of 1
Skill	What it can touch	Pattern check	Licence	Updated
os-big-pictureALWAYS invoke this skill when the user asks where the project as a whole stands - "where are we", "what's the big picture", "what have we built", "what is in this project", "map the project", "what does this thing even do", "what is stale", "what can we delete", "update the roadmap" - in any language, and whenever a session report has just been written. It keeps one file, BIG-PICTURE.md: what the product is, every feature with how far it got, which parts nobody has touched, and what is queued next. Age and wiring are measured from git; how far a feature got comes from the reports or says "not checked". Where a tracker is connected it offers to open the queue as tickets, after a yes and never before. Never invents work, never deletes code. Runs shell commands +2 more Pattern check: 1 item to reviewMITUpdated 4 Oct 2026	Runs shell commands Bundles scripts +1 more	Pattern check: 1 item to review	MIT	4 Oct 2026
os-what-could-go-wrongALWAYS invoke this skill before anything hard to undo gets agreed to - a contract, a purchase, a migration, a launch, a price change, a reorganisation - and whenever the user asks "what could go wrong", "what are we missing", "poke holes in this", or for a premortem or a red team, in any language. Assumes the decision already failed and works backwards to find out why, in a fresh agent that had no hand in making it. Sweeps nine areas and shows what each produced, including the empty ones. Ends on one verdict: go ahead, go but fix these first, try it small first, think again, do not do this. Runs shell commands +3 more Pattern check: 2 items to reviewMITUpdated 30 Sept 2026	Runs shell commands Bundles scripts +2 more	Pattern check: 2 items to review	MIT	30 Sept 2026