# proactive-agent

Turns AI agents into proactive assistants that suggest next steps, log decisions before context window compactions, and enforce security checks.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 632 installs · ★ 670
- Author: sundial-org
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sundial-org/awesome-openclaw-skills/tree/HEAD/skills/proactive-agent/SKILL.md
- Updated: 2026-03-07
- HTML: https://affpapa.org/en/nevibecode/skills/sundial-org-proactive-agent

## What it does

This skill shifts an assistant from waiting for instructions to suggesting project actions on its own. Using reverse prompting, it drafts proposals and waits for developer approval. Operating boundaries, project guidelines, and user preferences live directly in markdown files such as `SOUL.md` and `USER.md`.

Memory relies on a two-tier layout. Daily exchanges go into `memory/YYYY-MM-DD.md`, while distilled takeaways move into `MEMORY.md`. The workflow monitors the token limit with `session_status`. Once context consumption hits 70%, the agent dumps active context into daily logs, escalating to an emergency flush above 85% so nothing drops during context compaction.

Security follows strict data isolation. Incoming web pages, emails, or PDF documents remain data to inspect rather than commands to run. The agent halts and asks for approval before deleting files. Keep in mind that workspace setup requires copying the template files from `assets/` into the project root before first use.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill proactive-agent -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/proactive-agent/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/proactive-agent/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill proactive-agent -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/proactive-agent/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill proactive-agent -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/proactive-agent/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install sundial-org/awesome-openclaw-skills proactive-agent
```

2. **Manually: put the files in place**
- File: `.github/skills/proactive-agent/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill proactive-agent -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/sundial-org/awesome-openclaw-skills --path skills/proactive-agent
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/proactive-agent/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add sundial-org/awesome-openclaw-skills --skill proactive-agent -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/sundial-org/awesome-openclaw-skills/tree/HEAD/skills/proactive-agent/SKILL.md

## When to use it
- preserve key decisions before context window compaction
- configure user preferences and agent boundaries via ONBOARDING.md
- prevent code execution from untrusted external documents
- receive proactive suggestions without drafting manual prompts

## Example prompts
- Check context levels with session_status and flush key notes to disk
- Start onboarding in interactive mode to populate USER.md
- Run the security audit script to verify workspace rules

## Similar
- [remember](https://affpapa.org/en/nevibecode/skills/rohitg00-remember.md) — skill · 14000 installs
- [handoff](https://affpapa.org/en/nevibecode/skills/rohitg00-handoff.md) — skill · 13400 installs
- [mantis-summarize](https://affpapa.org/en/nevibecode/skills/mantis-summarize.md) — skill · 1600 installs
- [how-it-works](https://affpapa.org/en/nevibecode/skills/how-it-works.md) — skill · 5100 installs
- [context-engineering-collection](https://affpapa.org/en/nevibecode/skills/context-engineering-collection.md) — skill · 4200 installs
- [wrap-up](https://affpapa.org/en/nevibecode/skills/codewithmukesh-wrap-up.md) — skill · 2800 installs

## Other versions with the same name
- [proactive-agent · halthelobster](https://affpapa.org/en/nevibecode/skills/proactive-agent.md) — 15100 installs

From the same set: [sundial-org/awesome-openclaw-skills](https://affpapa.org/en/nevibecode/by/sundial-org/awesome-openclaw-skills.md) — 12 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md