Skip to content
Back to skills

Claude Collaborator

ASecurity

Coordinate with Claude Code CLI (claude.exe) via Herdr to cross-validate changes, request second-opinion reviews on git diffs, or validate test runs.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 6, 2026
ai-agentsbashgitsecurity

Works with

  • claude code
  • cli

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add bepaldes/heimdall-agent --skill claude-collaborator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claude Collaborator?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Claude Collaborator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bepaldes-claude-collaborator/badge)](https://www.skillsdirectory.com/skills/bepaldes-claude-collaborator)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: claude-collaborator
description: Coordinate with Claude Code CLI (claude.exe) via Herdr to cross-validate changes, request second-opinion reviews on git diffs, or validate test runs.
---

# Claude Collaborator Skill

This skill enables Antigravity (Gemini) to orchestrate tasks with Claude Code (`claude.exe`) directly through native Herdr multiplexing, delegating complex architectural reasoning, diff reviews, and adversarial validation.

## When to Activate

- When the user asks to "review with Claude", "validate with Claude", or "get a second opinion from Claude".
- After making non-trivial code edits or architectural refactors, to verify there are no hidden regressions.
- When facing ambiguous design choices where a second model's critique helps pick the best approach.

## Orchestration Method: Native Herdr Agent (`herdr` skill)

When running inside Herdr (`$env:HERDR_ENV = "1"`), communicate directly using Herdr's native agent orchestration. This maintains a persistent session across turns, preserves context, respects interactive approvals (`blocked`), and handles bracketed paste:

### 1. Fast Path: Re-use Active Idle Agent
Before splitting a pane, check if a Claude agent is already running and idle:
```bash
herdr agent list
```
If an agent named `claude-reviewer` or `claude` is idle or done, prompt it directly:
```bash
herdr agent prompt claude-reviewer "Review the latest changes." --wait --timeout 120000
```

### 2. Spawning a New Claude Agent (Single-Execution Batch)
If no active Claude agent exists, batch pane creation and agent startup in a single command:
```bash
PANE_ID=$(herdr pane split --current --direction right --cwd "$PWD" --no-focus | jq -r '.result.pane.pane_id')
herdr agent start claude-reviewer --kind claude --pane "$PANE_ID" -- --model claude-sonnet-5
herdr agent prompt claude-reviewer "Review git diff for security regressions and type errors." --wait --timeout 120000
```

### 3. Read Findings into Context
```bash
herdr agent read claude-reviewer --source recent-unwrapped --lines 120
```

### 4. Interactive Collaboration
When an interactive session or clarification is needed, send keys or prompt interactively:
```bash
herdr agent send-keys claude-reviewer enter
```

## Guidelines for Antigravity

- **Synthesize, Don't Blindly Echo**: When Claude returns feedback, analyze its critiques against the platform's requirements (`docs/03.REQUIREMENTS.md`, `docs/06.DECISIONS.md`, `docs/02.GLOSSARY.md`).
- **Iterate**: If Claude identifies valid issues (e.g. edge cases, unhandled promises, type mismatches), implement the fixes and run the validation again.
- **Report**: Present the consensus to the user with clear notes on what was improved.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.