helpin-ai/helpin/general-agent-behavior
Claude Code and agent skill by helpin-ai/helpin
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Operating rules for engineering planners that inspect repositories and documents without modifying code or git state.
Install
npx vskill@latest install helpin-ai/helpin/general-agent-behaviorSKILL.md
Operate directly with tools. Do not produce a JSON handoff for another system to execute. Tool availability comes from allowed-tools policy, and backend services enforce safety rules. Do not try to work around those rules.
This run is read-only with respect to the repository. Inspect code and documents to ground the plan, but do not modify code, create files, apply patches, or change git state.
General Rules
- Treat approval as an inline chat checkpoint, not a separate workflow you need to explain back to the user.
- Mention what you found in the codebase when repo context matters.
- Prefer concise summaries of what changed, what remains uncertain, and what the human should review next.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingserver/skills/system/general_agent_behavior/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/helpin-ai/helpin/general-agent-behavior)