Async Repl Protocol

If you're testing Claude skills with Agentica's async REPL harness, this prevents common async/await mistakes that silently break your code. It enforces two critical rules: always await tool calls that return futures (like view_file or ask_memory), and keep your logic in a single code block since the REPL only executes the first one. The second rule catches people off guard because splitting compute and return across blocks feels natural but means your return statement never runs. It's narrowly scoped to this specific testing environment, so you won't invoke it directly, but it'll save you from debugging why your tests are failing mysteriously when the issue is just missing await keywords or block splitting.

skills.sh installs: 478
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill async-repl-protocol --agent claude-code

Installs into .claude/skills of the current project.

Files

Async REPL Protocol

When working with Agentica's async REPL harness for testing.

Rules

1. Use `await` for Future-returning tools

content = await view_file(path)  # NOT view_file(path)
answer = await ask_memory("...")

2. Single code block per response

Compute AND return in ONE block. Multiple blocks means only first executes.

# GOOD: Single block
content = await view_file(path)
return any(c.isdigit() for c in content)

# BAD: Split blocks (second block never runs)
content = await view_file(path)

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly