Home/Skills/Development Tools/Perry Coding Agents
gricha

Perry Coding Agents

7 versions
gricha·Jan 24, 2026

Summary

TL;DR: Dispatches coding tasks to AI agents running on Perry cloud workspaces, letting you run multiple coding agents in parallel on separate tasks.

Perry Coding Agents is an OpenClaw skill that dispatch coding tasks to OpenCode or Claude Code on Perry workspaces. Use for development work, PR reviews, or any coding task requiring an isolated environment.

Created by gricha, this skill has been downloaded 4k+ times on ClawHub. Install it with one command and your AI agent gains these capabilities right away. Learn how to add skills for setup steps.

Use cases

  • Run multiple bug fixes in parallel across different parts of a codebase
  • Dispatch a refactoring task to a separate workspace while continuing other work
  • Coordinate feature development across several microservices simultaneously
  • Set up a pipeline where one agent reviews code produced by another agent

Installation

Run this command to install the skill on your OpenClaw agent:

Install with OpenClaw
npx clawhub@latest install perry-coding-agents
Downloads
3.5k
Active installs
11
Stars
2
Updated
Jan 24, 2026

Security scan

Security scan
VirusTotalSuspicious
View report
OpenClawSuspicioushigh confidence

The skill's instructions match its stated purpose (dispatch coding tasks to remote Perry workspaces) but omit and contradict important operational requirements (missing required binaries and secret/token handling) and recommend insecure SSH options—these mismatches warrant caution before installing.

Purpose & Capability
Instruction Scope
Install Mechanism
Credentials
Persistence & Privilege

SKILL.md

SKILL.md
---
name: perry-coding-agents
description: Dispatch coding tasks to OpenCode or Claude Code on Perry workspaces. Use for development work, PR reviews, or any coding task requiring an isolated environment.
metadata: {"clawdbot":{"emoji":"🛠️"}}
---

# Perry Coding Agents

Dispatch tasks to OpenCode/Claude Code on Perry workspaces.

## Rules
- **Always create dex task FIRST** — before any dispatch, no exceptions
- **No hard timeouts** — background dispatch, let agent run
- **Use IPs** — MagicDNS broken in containers (`tailscale status` for IPs)
- **One task per PR** — same session continues until done
- **Reuse sessions** — OpenCode keeps context in `~/.opencode/`
- **Never code directly** — always dispatch to agents

## Commands
```bash
# OpenCode (primary)
ssh -o StrictHostKeyChecking=no workspace@<IP> "cd ~/<project> && /home/workspace/.opencode/bin/opencode run 'task'" &

# Claude Code (needs TTY)
ssh -t workspace@<IP> "cd ~/<project> && /home/workspace/.local/bin/claude 'task'"
```

## Dispatch Pattern
```bash
WAKE_IP=$(tailscale status --self --json | jq -r '.Self.TailscaleIPs[0]')

ssh -o StrictHostKeyChecking=no workspace@<IP> "cd ~/<project> && /home/workspace/.opencode/bin/opencode run 'Your task.

When done: curl -X POST http://${WAKE_IP}:18789/hooks/wake -H \"Content-Type: application/json\" -H \"Authorization: Bearer <hooks-token>\" -d \"{\\\"text\\\": \\\"Done: summary\\\", \\\"mode\\\": \\\"now\\\"}\"
'" &
```

## Task Tracking
Create task before dispatch with: workspace IP, branch, goal, done criteria.
Same task until CI green. Complete with result summary.

## Example: Full PR Flow

```bash
# 1. Create task
# Track: workspace feat1 (100.109.173.45), branch feat/auth, goal: add auth

# 2. Get wake info
WAKE_IP=$(tailscale status --self --json | jq -r '.Self.TailscaleIPs[0]')

# 3. Dispatch (background, no timeout)
ssh -o StrictHostKeyChecking=no workspace@100.109.173.45 "cd ~/perry && /home/workspace/.opencode/bin/opencode run 'Add bearer token auth to all API endpoints. Create PR when done.

When finished: curl -X POST http://${WAKE_IP}:18789/hooks/wake -H \"Content-Type: application/json\" -H \"Authorization: Bearer <token>\" -d \"{\\\"text\\\": \\\"Done: Auth PR created\\\", \\\"mode\\\": \\\"now\\\"}\"
'" &

# 4. Wake received → check CI
ssh workspace@100.109.173.45 "cd ~/perry && gh pr checks 145"

# 5. CI fails → dispatch follow-up (same task, agent has context)
ssh -o StrictHostKeyChecking=no workspace@100.109.173.45 "cd ~/perry && /home/workspace/.opencode/bin/opencode run 'CI failing: test/auth.test.ts line 42. Fix and push.

When fixed: curl -X POST http://${WAKE_IP}:18789/hooks/wake ...'" &

# 6. CI green → complete task with result
```

## Troubleshooting
- **Can't reach**: `tailscale status | grep <name>`
- **Commands not found**: Use full paths (`/home/workspace/.opencode/bin/opencode`)
- **Wake not firing**: Check IP/token, test with curl

Version history

v1.5.0Latest
Jan 24, 2026

Emphasized: always create dex task BEFORE dispatch

v1.4.0
Jan 24, 2026

Added concrete end-to-end example

v1.3.0
Jan 24, 2026

Trimmed 5KB to 1.7KB - more concise

v1.2.0
Jan 24, 2026

Added learnings: no timeouts, task tracking, session reuse, use IPs

v1.1.1
Jan 23, 2026

fix: correct webhook endpoint (/hooks/wake) and use hooks.token instead of gateway.auth.token

v1.1.0
Jan 22, 2026

Fix: use ~/projname not /workspace, document SSH PATH issues

v1.0.0
Jan 22, 2026

Initial release: Dispatch tasks to OpenCode/Claude Code on Perry workspaces

Frequently asked questions

Yes. The skill dispatches work to Perry cloud workspaces, so you need an active Perry account with available workspace capacity.

Installation method

Send this prompt to your agent to install the skill

npx clawhub@latest install perry-coding-agents
Download ZIP

Skill info

Versionv1.5.0
Authorgricha
UpdatedJan 24, 2026
SecuritySuspicious

Files

SKILL.md2.9 KB

Run OpenClaw in the cloud

Deploy in seconds. Skills pre-installed.

See plans

Skill data sourced from ClawHub