Bayes Scorer — Testing & QA agent for Claude Code
Use this agent when a /bayes decision needs evidence gathered from files, logs, git history or test output before scoring — it reads with cheap tools, picks evidence codes, runs bayes.py once and retu.
How to install Bayes Scorer
Installs to ~/.claude/agents/haraldalder-vibemogger-bayes-gate-bayes-scorer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/haraldalder-vibemogger/bayes-gate/HEAD/agents/bayes-scorer.md -o ~/.claude/agents/haraldalder-vibemogger-bayes-gate-bayes-scorer.md Restart Claude Code, or start a new session, for it to be picked up.
What Bayes Scorer does
name: bayes-scorer description: Use this agent when a /bayes decision needs evidence gathered from files, logs, git history or test output before scoring — it reads with cheap tools, picks evidence codes, runs bayes.py once and returns only the compact table. Never use it for scoring that needs no file reading (the main agent calls bayes.py directly).
Context: A 500 error on /login; the main agent has three hypotheses but has not looked at logs or blame yet. user: "Find out why loAlternatives in Testing & QA
- Prod Incident Responder — Reads recent prod logs, picks the highest-impact recurring error, drafts a minimal fix PR with a regression te 324 ★
- Critical Thinking — Critical thinking mode that challenges assumptions and probes reasoning 100 ★
- Job Match Author — WRITE-access implementer for ATS scoring, job analysis, keyword/skill/requirement extraction, resume-job match 52 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Op Reviewer
Judgment-tier read-only reviewer and scorer, dispatched by the operator. Runs in spec mode, quality mode, or s
Bug Hypothesis Investigator
Use when one candidate cause of a defect needs a falsifiable test before anyone believes it. Give it the sympt
Log Digger
Triage high-volume output — cloud logs, container logs, test suite runs, build failures, long SQL result sets
Frugal Scout
Read-only search and extraction for /frugal. Finds files and symbols, reads logs, test output, docs, or pages,
Log Distiller
Distills test runs, build output, and log files into the few lines that matter. Use when raw output is too lar
Omelette Tester
Clean-context tester — takes the approved spec and the diff from git, writes tests, runs them through the real
Related Skills
Ronin Toolkit
Claude Code plugins for sysadmins and MSP techs. Run IT projects and troubleshooting in cheap, evidence-first
Agent Token Saver Skill Router
Your agent reads the few skills a task needs, not forty. Picks none, one, or a small bounded set, and leaves t
Diagnose Rota Routing
Explain why the rota gateway sent a request to a particular claude silo by reconstructing the scoring decision