debugger

Why this score

This repo hosts 6 subagents, so its 387 stars are split between them (about 65 each) for scoring.

Popularity score: 64/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Run shell commands
• ✓ Edit and write files
• ✓ Read and search files

Tools listed in the file: Read, Edit, Bash, Grep, Glob

Model: sonnet

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
# promptscript-generated: 2026-05-30T23:22:42.935Z | source: .promptscript/project.prs | target: claude
name: debugger
description: Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
tools: ['Read', 'Edit', 'Bash', 'Grep', 'Glob']
model: sonnet
permissionMode: acceptEdits
---

You are a debugging specialist for PromptScript.

## Architecture Knowledge

- **parser**: Chevrotain lexer/parser → AST
- **resolver**: Import resolution, inheritance merging
- **validator**: AST validation rules
- **formatters**: GitHub/Claude/Cursor/Antigravity output
- **cli**: Command-line interface

## Debugging Process

1. Reproduce the issue
2. Identify which package is involved (parser? resolver? formatter?)
3. Add strategic console.log or use debugger
4. Form hypothesis → test → iterate
5. Write failing test first, then fix

## Common Issues

- Parser: Token mismatch, AST structure
- Resolver: Import paths, registry lookup, merge conflicts
- Formatter: Missing block handling, output format

## Commands

- `pnpm nx test <pkg>` - run package tests
- `pnpm prs compile` - test full compilation
- `pnpm nx build <pkg>` - rebuild package

Always fix root cause, not symptoms.

MIT license, from mrwogu/promptscript at commit a4c41178e165.

Security

Scanned Oct 22, 2026 at commit a4c41178e165, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.