From bug-hunt
Run adversarial bug hunting on your codebase. Uses 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Invoke with /bug-hunt, /bug-hunt [path], or /bug-hunt -b <branch> [--base <base>].
How this skill is triggered — by the user, by Claude, or both
Slash command
/bug-hunt:bug-huntThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run a 3-agent adversarial bug hunt on your codebase. Each agent runs in isolation.
Run a 3-agent adversarial bug hunt on your codebase. Each agent runs in isolation.
/bug-hunt # Scan entire project
/bug-hunt src/ # Scan specific directory
/bug-hunt lib/auth.ts # Scan specific file
/bug-hunt -b feature-xyz # Scan files changed in feature-xyz vs main
/bug-hunt -b feature-xyz --base dev # Scan files changed in feature-xyz vs dev
The raw arguments are: $ARGUMENTS
Parse the arguments as follows:
-b <branch>: this is a branch diff mode.
-b.--base <base-branch> is also present, use that as the base branch. Otherwise default to main.git diff --name-only <base>...<branch> using the Bash tool to get the list of changed files.-b: treat the entire argument string as a path target (file or directory). If empty, scan the current working directory.You MUST follow these steps in exact order. Each agent runs as a separate subagent via the Agent tool to ensure context isolation.
Follow the rules in the Target section above to determine the scan target. If in branch diff mode, run the git diff command now and collect the file list.
Read these files using the skill directory variable:
Launch a general-purpose subagent with the hunter prompt. Include the scan target in the agent's task. If in branch diff mode, pass the explicit file list so the Hunter only scans those files (full contents). The Hunter must use tools (Read, Glob, Grep) to examine the actual code.
Wait for the Hunter to complete and capture its full output.
If the Hunter reported TOTAL FINDINGS: 0, skip Steps 4-5 and go directly to Step 6 with a clean report. No need to run Skeptic and Referee on zero findings.
Launch a NEW general-purpose subagent with the skeptic prompt. Inject the Hunter's structured bug list (BUG-IDs, files, lines, claims, evidence, severity, points). Do NOT include any narrative or methodology text outside the structured findings.
The Skeptic must independently read the code to verify each claim.
Wait for the Skeptic to complete and capture its full output.
Launch a NEW general-purpose subagent with the referee prompt. Inject BOTH:
The Referee must independently read the code to make final judgments.
Wait for the Referee to complete and capture its full output.
Display the Referee's final verified bug report to the user. Include:
If zero bugs were confirmed, say so clearly — a clean report is a good result.
npx claudepluginhub qkyrie/claude-setup --plugin bug-huntOrchestrates a three-phase adversarial code review with isolated agents (Hunter, Skeptic, Referee) to eliminate sycophancy and produce high-fidelity bug reports. Use for thorough code review, bug hunting, security audits.
Performs multi-agent code review of current git branch against main: detects bugs via specialist agents, verifies findings, ranks severity, generates persistent report before push/merge.
Runs a parallel fan-out of bug finders and a verify gate over a diff or path, producing ranked, verified instance-bug findings. Use for concrete defects in a PR, range, or directory.