Reviewer Merge — Development agent for Claude Code
Merge phase of deep-review — folds the surviving per-dimension findings into findings.md.
How to install Reviewer Merge
Installs to ~/.claude/agents/blazej-bryla-ai-coding-setup-reviewer-merge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/blazej-bryla/ai-coding-setup/HEAD/agents/reviewer-merge.md -o ~/.claude/agents/blazej-bryla-ai-coding-setup-reviewer-merge.md Restart Claude Code, or start a new session, for it to be picked up.
What Reviewer Merge does
name: reviewer-merge description: Merge phase of deep-review — folds the surviving per-dimension findings into findings.md. Spawned by deep-review's workflow; not for general use. model: sonnet effort: low disallowedTools: NotebookEdit
Read the per-dimension files under the review workdir you were given, keep only findings not marked `disproved`, and build `findings.md` exactly per step 3 ("Deduplicate and rank") of `~/.agents/skills/deep-review/SKILL.md`. Do not re-review the code and
Alternatives in Development
- Cold Verifier — Phase 11 cold verification agent that independently re-verifies CRITICAL and HIGH findings with zero prior con 125 ★
- Sub-Agent Tech Debt Finder & Fixer Command — A two-phase command that first identifies technical debt across your codebase, presents findings for review, t 116 ★
- Eval Judge — Use this agent during the /eval Skill Phase 3 (Epic #803, issue #810) to judge — from a session-eval record's 49 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Reviewer Refute
Refute phase of deep-review — tries to disprove one dimension's findings against the actual code. Spawned by d
Reviewer Codebase
Codebase-consistency reviewer for one change set. Spawned by deep-review (and its Reuse callers /work, /implem
Pan Meta Reviewer
Reviews the reviewer + hardener output. Flags things both missed, disputes findings that look overstated, and
Reviewer Dispatcher
Selects the weakest dimension from the most recent merge-probability-scorer output and runs the matching speci
Frontend Perf Reviewer
Use AFTER frontend code is written to review for Core Web Vitals / runtime-performance regressions. Reports se
Aiskills Code Reviewer
Reviews diffs and pull requests with visible per-dimension passes and severity-classified findings (Blocker/Ma
Related Skills
Review Cycle
Multi-reviewer review→fix cycle over one or more open PRs — parallel reviewers, structured findings, inline-vs
Vf Review
Parallel Salesforce code review of the diff against a base ref - dispatch the quality gate and security review
Buddhi Review
Automated multi-reviewer pull-request review for Claude Code: fan out AI reviewers, classify findings, guide f