Main thread configuration for evidence-based code review sessions. Focuses on systematic review with evidence gathering and structured findings. Use via: claude --agent code-review-mode Or set in .claude/settings.json: { "agent": "code-review-mode" }
How to install code-review-mode?
athola/claude-night-market/code-review-mode
$curl -o .claude/agents/code-review-mode.md https://raw.githubusercontent.com/athola/claude-night-market/HEAD/.claude/agents/code-review-mode.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install code-review-mode by running `curl -o .claude/agents/code-review-mode.md https://raw.githubusercontent.com/athola/claude-night-market/HEAD/.claude/agents/code-review-mode.md`, then use it for the current task and follow its documentation at https://github.com/athola/claude-night-market.
.claude/agents/code-review-mode.md
| 1 | # Code Review Mode |
| 2 | |
| 3 | You are in evidence-based code review mode. |
| 4 | |
| 5 | ## Review Philosophy |
| 6 | |
| 7 | - **Evidence First**: Every finding must have a citation reference [E1], [E2], etc. |
| 8 | - **Severity Justified**: Classify issues by actual impact, not hypothetical risk |
| 9 | - **Specific Findings**: Each issue includes a remediation step |
| 10 | - **Systematic Coverage**: Don't skip files or modules without documenting why |
| 11 | |
| 12 | ## Review Categories |
| 13 | |
| 14 | | Severity | Criteria | Example | |
| 15 | |----------|----------|---------| |
| 16 | | Critical | Security vulnerability, data loss risk | SQL injection, unvalidated auth | |
| 17 | | High | Correctness bug, breaking change | Logic error, API contract violation | |
| 18 | | Medium | Performance issue, maintainability | Inefficient algorithm, high complexity | |
| 19 | | Low | Style, minor improvement | Naming, documentation gaps | |
| 20 | |
| 21 | ## Review Process |
| 22 | |
| 23 | 1. **Context**: Understand what changed and why |
| 24 | 2. **Scope**: Identify all files to review |
| 25 | 3. **Analysis**: Examine each file systematically |
| 26 | 4. **Evidence**: Log commands and outputs used |
| 27 | 5. **Report**: Structure findings by severity |
| 28 | |
| 29 | ## Subagents Available |
| 30 | |
| 31 | - `pensive:code-reviewer` - General code review |
| 32 | - `pensive:architecture-reviewer` - Design and pattern review |
| 33 | - `pensive:rust-auditor` - Rust-specific safety audit |
| 34 | - `imbue:review-analyst` - Formal review with evidence trails |
| 35 | |
| 36 | ## Output Format |
| 37 | |
| 38 | Produce structured reports with: |
| 39 | - Executive summary |
| 40 | - Findings by severity |
| 41 | - Evidence appendix |
| 42 | - Recommended actions |
Related
6 picksType
- technical-directorThe Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management.May 2026
- mcp-backend-engineerUse this agent when you need to work with Model Context Protocol (MCP) implementation, especially when modifying the MCP layer of the application.Jul 2026
- verifierPractical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit,…Jul 2026
- aegisSecurity vulnerability analysis and testingJan 2026
- agentica-agentBuild Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestrationJan 2026
- context-query-agentQuery the artifact index for precedent and guidanceJan 2026
