Baseline Reviewer — Development agent for Claude Code
Read-only reviewer for changes to this plugin — skills, agent definitions, manifests, hooks and eval cases.
How to install Baseline Reviewer
Installs to ~/.claude/agents/jakos-claude-baseline-baseline-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/jakos/claude-baseline/HEAD/.claude/agents/baseline-reviewer.md -o ~/.claude/agents/jakos-claude-baseline-baseline-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Baseline Reviewer does
name: baseline-reviewer description: Read-only reviewer for changes to this plugin — skills, agent definitions, manifests, hooks and eval cases. Checks the things that fail silently here: a hook that loads but does nothing, a description that will not trigger, a claim no rubric tests. Use before committing in claude-baseline. Reports findings; never edits. tools: Read, Grep, Glob, Bash disallowedTools: Edit, Write, NotebookEdit model: sonnet color: cyan
You review changes to `claude-bas
Alternatives in Development
- Claude Code Hook Agent — Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions 321 ★
- PR Check Watcher — Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary 289 ★
- Sanitizer — Generic sanitizer worker agent 262 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Gaia System
Use when building, modifying, or auditing Gaia's own machinery — agents, skills, hooks and hook modules, routi
Eval Case Auditor
Read-only auditor for triage eval cases. Use after adding several cases or before promoting a baseline. Report
Hooks Enhancer
Analyze hook definitions for safety and best practices
Plugin Validator
Validate plugin structure, manifests, hook configs, and marketplace consistency for this agent-toolkit repo. U
Codebase Historian
Expert on how the existing system ACTUALLY works today. Traces real code paths, finds where a change should ho
Fixture Builder
Creates and enriches eval suite fixtures — .md component files, .metadata.yaml grading criteria, and .rubric.y
Related Skills
Eval Prompts
Run a golden-set prompt eval suite against the pinned baseline; fail on any regression beyond threshold.
Claude Skills Pitfalls
Things that silently break your Claude skill, and how to fix them.
Always Loaded Diet
Discipline for the files your agent loads every session (CLAUDE.md, MEMORY.md): one nightly writer, measured b