Keepr — Development agent for Claude Code
Use this agent to evaluate PR review comments and classify them into actionable recommendations.
How to install Keepr
Installs to ~/.claude/agents/lucasxf-engineering-daybook-keepr.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/lucasxf/engineering-daybook/HEAD/.claude/agents/keepr.md -o ~/.claude/agents/lucasxf-engineering-daybook-keepr.md Restart Claude Code, or start a new session, for it to be picked up.
What Keepr does
name: keepr description: Use this agent to evaluate PR review comments and classify them into actionable recommendations. keepr (keeper of code quality) reads code context, applies the four-axis evaluation framework, and returns Accept/Reject/Defer/Question verdicts with rationale. Invoked by /review-pr after comments are fetched and delta-skipped. Input: list of comments with file:line references. Output: evaluated, classified, grouped recommendations ready for user confirmation. model: son
Alternatives in Development
- Gitnexus Branch Hygiene Reviewer — GitNexus branch hygiene and mergeability reviewer 45.8k ★
- Correction Sweep — Find every note restating a corrected fact and classify each as authoritative, restatement, or historical 4.6k ★
- Support Triage — Classify inbound support email (.eml in Downloads) into bug / feature-request / billing / how-to / spam / urge 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Uxaudit L4 Judge
L4-journey Judge for the uxaudit pipeline. Reads the per-journey capture directory (screenshots + steps.json +
George
Factory floor foreman with four modes. (1) Status Report — runs the factory dashboard, interprets metrics, and
PR Review Analyst
Validates PR review comments for correctness, severity, and recommendation quality using full codebase context
Review Axis
One axis of a code review, dispatched by the review-changes skill. Reads a diff against a single question — co
Appraiser
Use for deep-dive evaluation of one specific job posting — the "evaluate and then ask me" flow. Trigger when t
Issue Feature Review
Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and imple
Related Skills
Context Health Check
Run a structured health check on the current conversation context and report its quality score with actionable
Vibememo Eval
Periodic VibeMemo evaluation and capture. Runs on a loop (default 30m) to assess whether significant decisions
Creative Director Skill
AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synec