Stats
Actions
Tags
From bopen-tools
Orchestrates 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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bopen-tools:hunter-skeptic-refereeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
An adversarial code review workflow designed by danpeguine (@danpeguine). Three agents run in isolated contexts — no agent sees what any other agent "wants" to hear. This eliminates sycophantic confirmation bias and produces ground-truth bug reports.
An adversarial code review workflow designed by danpeguine (@danpeguine). Three agents run in isolated contexts — no agent sees what any other agent "wants" to hear. This eliminates sycophantic confirmation bias and produces ground-truth bug reports.
User command: /bug-hunt [path | -b branch [--base base]]
When a single agent both finds bugs and evaluates them, it anchors on its own earlier judgments. By resetting context between phases and giving each agent only what it needs, every verdict is genuinely independent. The Skeptic cannot see the Hunter's enthusiasm. The Referee cannot see the Skeptic's skepticism.
| Phase | Agent | Subagent Type | Role |
|---|---|---|---|
| 1. Hunter | Nyx | bopen-tools:code-auditor | Find every possible bug. Maximize recall. False positives OK. |
| 2. Skeptic | Kayle | bopen-tools:architecture-reviewer | Challenge every finding. Risk/EV calculation. 2x penalty for wrong dismissals. |
| 3. Referee | Iris | bopen-tools:tester | Final arbiter. Read code independently. Produce ground truth. |
The skill supports two modes:
Path mode (default): Scan a file, directory, or the entire project.
/bug-hunt # Entire project
/bug-hunt src/ # Directory
/bug-hunt lib/auth.ts # Specific file
Branch diff mode (-b): Scan only files changed between branches. Reads full file contents, not just diffs.
/bug-hunt -b feature-xyz # vs main
/bug-hunt -b feature-xyz --base dev # vs dev
For branch diff mode: git diff --name-only <base>...<branch> to get the file list.
| Score | Meaning |
|---|---|
| +1 | Low — minor edge case, cosmetic, code smell |
| +5 | Medium — functional issue, data inconsistency, missing validation |
| +10 | Critical — security vulnerability, data loss, race condition, crash |
EV = (confidence% × points) - ((100 - confidence%) × 2 × points)All three agents use a consistent BUG-ID format for cross-phase traceability:
Hunter output:
**BUG-[N]** | Severity: [Low/Medium/Critical] | Points: [1/5/10]
- **File:** [path]
- **Line(s):** [number or range]
- **Category:** [logic|security|error-handling|concurrency|edge-case|performance|data-integrity|type-safety|other]
- **Claim:** [one sentence]
- **Evidence:** [code quote]
Skeptic output:
**BUG-[N]** | Original: [points] pts
- **Counter-argument:** [technical argument citing code]
- **Evidence:** [code quote]
- **Confidence:** [0-100]%
- **Risk calc:** EV = ...
- **Decision:** DISPROVE / ACCEPT
Referee output:
**BUG-[N]**
- **Hunter's claim:** [summary]
- **Skeptic's response:** [DISPROVE/ACCEPT + summary]
- **Your analysis:** [independent assessment]
- **VERDICT: REAL BUG / NOT A BUG**
- **Confidence:** High / Medium / Low
- **True severity:** [Low/Medium/Critical]
- **Suggested fix:** [brief direction]
Parse arguments for path mode vs branch diff mode. In branch diff mode, run git diff --name-only to get the file list.
Dispatch bopen-tools:code-auditor with the target scope. The Hunter uses Glob/Read/Grep to examine actual code. Must NOT speculate about unread files.
If Hunter reports TOTAL FINDINGS: 0, skip Skeptic and Referee. Present a clean report directly.
Dispatch bopen-tools:architecture-reviewer with ONLY the structured bug list (BUG-IDs, files, lines, claims, evidence, severity). Do NOT pass the full codebase or any narrative text. The Skeptic reads code independently.
Dispatch bopen-tools:tester with the Hunter's full report AND the Skeptic's full report. The Referee reads code independently.
Display the Referee's verified report:
<details> section with dismissed bugs for transparencyA clean report (zero confirmed bugs) is a valid result — say so clearly.
| Phase | Gets access to |
|---|---|
| Hunter (Nyx) | Full codebase (or changed files in branch diff mode) |
| Skeptic (Kayle) | Structured bug list + referenced file paths only |
| Referee (Iris) | Hunter findings + Skeptic verdicts only |
Violating these boundaries reintroduces the sycophancy problem. If the Skeptic sees the Hunter's confidence, it anchors on it. If the Referee sees either agent's emotional register, it drifts toward consensus rather than truth.
-b mode)For quick informal reviews, just use Nyx directly in normal mode.
npx claudepluginhub b-open-io/claude-plugins --plugin bopen-toolsReviews diffs, PRs, and agent output for bugs, security issues, mocks, and code quality. Automates codebase audits with domain-specific checks and deep scanning.
Reviews code changes adversarially using parallel layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with triage into actionable categories. Invoke on 'run code review' or 'review this code'.
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.