systematic-debugger
Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI", "intermittent failure", "need a 5-why". Escalation chain: build-error-resolver owns compile-time/build errors upstream of this agent; this agent owns reproducible runtime bugs; if the bisect is inconclusive, or the failure is flaky, environment-dependent, or spans multiple systems, escalate to rca-debugger; escalation-fixer is the last resort with architectural authority. Not for compile errors (build-error-resolver) or runtime performance profiling (performance-reviewer).
Tools
read, edit, bash, grep, glob, write, mcp__chrome-devtools__list_console_messages, mcp__chrome-devtools__get_network_request, mcp__playwright__browser_console_messages
Model & source
sonnet
sangrokjung/claude-forge
Install
Paste this once. It creates ~/.claude/agents/, adds Claude Code if it is missing, and writes the file at the reviewed commit.
{ command -v claude >/dev/null || curl -fsSL https://claude.ai/install.sh | bash; } && mkdir -p ~/.claude/agents && curl -fsSL "https://raw.githubusercontent.com/sangrokjung/claude-forge/34d881dc9bdc669aadc3a1e8147a4bd5467ecbe3/agents/systematic-debugger.md" -o ~/.claude/agents/systematic-debugger.md && echo "agent installed: systematic-debugger"Windows (PowerShell):
New-Item -ItemType Directory -Force "$env:USERPROFILE\.claude\agents" | Out-Null; iwr "https://raw.githubusercontent.com/sangrokjung/claude-forge/34d881dc9bdc669aadc3a1e8147a4bd5467ecbe3/agents/systematic-debugger.md" -OutFile "$env:USERPROFILE\.claude\agents\systematic-debugger.md"
Then run claude and ask for the task — the agent is picked by its description.
Source
agents/systematic-debugger.md in sangrokjung/claude-forge, pinned at 34d881dc9bdc, license MIT.
Checked for hidden characters, outbound commands and self-installing shells — not a security audit. The agent runs with the tools listed above.