# kharmanskyi/open-steps

> A pack of skills for coding agents (Claude Code, Codex, Cursor, Gemini CLI) that rewrites their technical reports into plain language: clear summaries, verdicts and next steps for non-engineers.

- Magnitude: 2.0 out of 10 — Steady
- Stars: 871 total · +0 stars today, ≈ 26 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Shell · License: MIT · Created: 2026-08-25 · Last push: 2026-09-14
- GitHub: https://github.com/kharmanskyi/open-steps · Homepage: https://opensteps.ai · Page: https://gitnova.dev/en/r/kharmanskyi/open-steps

## Useful for

- Install the pack as a Claude Code plugin and verify that skills and hooks are wired
- Get a plain-language done-or-not report from the agent instead of commit hashes and jargon
- Copy the skills into ~/.agents/skills to use them in Codex, Cursor and Gemini CLI

## Why it’s here

- 0 stars so far today, about 26 expected by the end of the day.
- The repository is 29 days old and already has 871 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 85
- Issues and pull requests: 40
- Watchers: 37
- Average over the last week: 58 per day
- Usual pace: 16 per day
- Stars in the last hour (measured): 1
- Latest release: v0.4.3 (2026-09-14)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-25 … 2026-09-23: 13, 13, 10, 25, 41, 13, 8, 21, 19, 19, 18, 30, 20, 17, 22, 36, 4, 25, 10, 5, 10, 29, 86, 62, 72, 97, 81, 34, 31, 0

## More in this category

1. **unreallabsai/unreal-agent** — 8.8 · Early signal · AI agents · Go · +0 stars today, ≈ 841 by evening
   Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components.
   Full card: https://gitnova.dev/en/r/unreallabsai/unreal-agent.md
2. **NandhaKishorM/laya** — 8.7 · Breakout · AI agents · Python · +0 stars today, ≈ 3,806 by evening
   Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md
3. **google/ax** — 8.6 · Breakout · AI agents · Go · +0 stars today, ≈ 1,047 by evening
   A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and restricts network…
   Full card: https://gitnova.dev/en/r/google/ax.md
4. **CopilotKit/openmuse** — 8.4 · Early signal · AI agents · TypeScript · +0 stars today, ≈ 767 by evening
   A personal AI agent with a browser, terminal, and files that carries out tasks on request and shows its work. Built with CopilotKit and AG-UI for iOS, Android, and web.
   Full card: https://gitnova.dev/en/r/CopilotKit/openmuse.md
5. **jev-chat/jev-chat-jarvis** — 8.2 · Breakout · AI agents · Kotlin · +0 stars today, ≈ 1,709 by evening
   Android app that reads the on-screen chat via AccessibilityService, judges the other side's intent with the Jev model, and shows 3 ranked reply drafts in a translucent overlay. Replies are filled into the input box but sent manually.
   Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-23 01:59 UTC, updated every 30 minutes.