gpt4omni

Stallguard — Development skill for Claude Code

Development community

Drop-in wrapper that streams agent steps and kills/flags stalls, loops, and fake-GOAL finishes.

How to install Stallguard

This entry records only its repository, not the path inside it, so there is no exact command to give. Open gpt4omni/stallguard and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Stallguard does

Drop-in wrapper that streams agent steps and kills/flags stalls, loops, and fake-GOAL finishes.

Alternatives in Development

02 Runtime Shims — Prompt 02: Runtime Shims for bun:bundle Feature Flags & MACRO Globals 2.3k ★
Stop Review Gate — You are reviewing uncommitted changes before the author finishes their turn 664 ★
Obsidian Board — Show or update a kanban board — flags overdue items, updates from conversation 277 ★

README

stallguard

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](pyproject.toml) [![No dependencies](https://img.shields.io/badge/deps-zero-brightgreen.svg)](stallguard/) [![CI](https://github.com/gpt4omni/stallguard/actions/workflows/test.yml/badge.svg)](https://github.com/gpt4omni/stallguard/actions/workflows/test.yml)

**Your coding agent says "done". Did it do anything?** stallguard is a drop-in wrapper that streams agent steps, kills stalls and retry-loops, and flags fake-GOAL finishes — with a shareable trace for every run.

![stallguard demo](demo.gif)

pipx install stallguard
stallguard run -- npx claude-code "fix the login bug"
# [stallguard] status=ok exit=0 duration=42.1s trace=traces/stallguard-....html

No code changes. Just prefix your agent command with `stallguard run --`.

The problem

AI coding agents fail in three boring, expensive ways:

Stalls — no output for 20 minutes while your CI minute-burn ticks.
Loops — the same tool call retried 500 times (retrying with same args...).
Fake-GOALs — prints DONE ✅ while git diff is empty.

Logs scroll by, nobody watches, green checkmarks lie. stallguard turns each run into a verdict: `ok`, `error`, `stalled`, `looped`, or `fake-goal` — enforced by exit code, so CI can act on it.

30-second quickstart

# any agent, any command — just prefix it
stallguard run -- python -u your_agent.py
stallguard run --stall-timeout 90 --require-diff -- ./run.sh

# inspect a run later
stallguard view traces/stallguard-*.jsonl
# open traces/stallguard-*.html in a browser for the full step-by-step trace

What it catches

flag	default	catches	exit
`--stall-timeout N`	120	no output for N seconds → `SIGKILL`	124
`--repeat-limit K`	15	K identical lines in a row → `SIGKILL`	125
`--require-diff`	off	exit 0 + "done" text but em