perry-coding-agentsDispatch coding tasks to OpenCode or Claude Code on Perry workspaces. Use for development work, PR reviews, or any coding task requiring an isolated environment.
Install via ClawdBot CLI:
clawdbot install gricha/perry-coding-agentsDispatch tasks to OpenCode/Claude Code on Perry workspaces.
tailscale status for IPs)~/.opencode/# 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'"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\\\"}\"
'" &Create task before dispatch with: workspace IP, branch, goal, done criteria.
Same task until CI green. Complete with result summary.
# 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 resulttailscale status | grep /home/workspace/.opencode/bin/opencode)Generated Mar 1, 2026
A development team uses Perry Coding Agents to automate coding tasks like feature implementation or bug fixes during sprints. The agent dispatches tasks to isolated workspaces, allowing developers to focus on high-level design while ensuring code is produced in a controlled environment. This accelerates development cycles and maintains code quality through consistent execution.
A tech company integrates Perry Coding Agents to handle pull request reviews and CI/CD pipeline checks. The agent dispatches review tasks to OpenCode or Claude Code, analyzing code changes and providing feedback without manual intervention. This reduces review bottlenecks and ensures faster deployment cycles with automated quality assurance.
A coding bootcamp or online learning platform employs Perry Coding Agents to provide students with automated coding exercises and project feedback. The agent dispatches tasks to isolated environments, allowing students to practice coding in real-world scenarios without setup overhead. This enhances learning efficiency and scales instructor support.
An enterprise undergoing digital transformation uses Perry Coding Agents to automate the refactoring or migration of legacy codebases. The agent dispatches coding tasks to update APIs, integrate new libraries, or fix security vulnerabilities in isolated workspaces. This minimizes risk and accelerates modernization efforts with consistent execution.
A freelance developer leverages Perry Coding Agents to manage multiple client projects by dispatching coding tasks to dedicated workspaces. The agent handles routine development work, such as implementing features or debugging, while the freelancer oversees progress and client communication. This increases productivity and allows handling more projects simultaneously.
Offer Perry Coding Agents as a cloud service with tiered subscriptions based on usage limits, such as tasks per month or workspace hours. Revenue comes from monthly or annual fees, targeting small to medium-sized development teams. This model ensures predictable income and scales with customer growth through automated billing.
Sell Perry Coding Agents under enterprise licenses with custom pricing for large organizations needing high-volume task dispatch and dedicated support. Revenue is generated through one-time license fees or annual contracts, including premium features like advanced analytics and integration support. This model caters to industries with strict compliance and security requirements.
Implement a pay-per-use model where customers are charged based on the number of tasks dispatched or compute time consumed in Perry workspaces. Revenue accrues from microtransactions, appealing to freelancers or startups with variable workloads. This flexible pricing encourages adoption without upfront commitments.
💬 Integration Tip
Ensure proper Tailscale setup for IP access and use full command paths to avoid issues in containerized environments. Always create dex tasks first to track progress and reuse sessions for context retention.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.