Sb Experimenter Low — Testing & QA agent for Claude Code
strictlybetter experimenter pinned to LOW reasoning effort.
How to install Sb Experimenter Low
Installs to ~/.claude/agents/nagisanzenin-strictlybetter-sb-experimenter-low.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/nagisanzenin/strictlybetter/HEAD/agents/sb-experimenter-low.md -o ~/.claude/agents/nagisanzenin-strictlybetter-sb-experimenter-low.md Restart Claude Code, or start a new session, for it to be picked up.
What Sb Experimenter Low does
name: sb-experimenter-low description: "strictlybetter experimenter pinned to LOW reasoning effort. MUST BE USED by /strictlybetter:run for the config, docs, and test-add operators: knob and flag changes, documentation, adding a test that captures a case. Fresh-context per experiment: implements exactly one pre-registered hypothesis inside one worktree, sees no other experiment, no holdout, no confirm numbers; returns DONE or BLOCKED: . Byte-identical to the other sb-experimente
Alternatives in Testing & QA
- Track Plan — Track ID: {{TRACK_ID}} Spec: spec.md Estimated Effort: {{EFFORT_ESTIMATE}} 31.9k ★
- Fable Verifier — Cold verifier for finished fable deliverables 837 ★
- Backend Unit Tests — Add focused backend unit tests aligned with current package test conventions 720 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Quick Executor
Executes small, low-risk, mechanical tasks fast — typo fixes, copy/i18n tweaks, config value changes, single-f
Product Docs
Creates and updates process docs, templates, decision artifacts, and agent specs. TRIGGER when: (1) task adds
AI Prompt Architect
Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/decisions/ADR-{
Doc Test Alignment
Audits a staged/branch diff for new public API surface (exceptions, classes, public functions, CLI commands, I
Fast Worker
Mechanical, low-risk bulk work, mechanical edits, inventory sweeps, repetitive migrations, generated-file main
Agency Evidence Collector
Screenshot-obsessed QA — vyžaduje visual proof pro každý claim. Default 3-5 issues found, "zero issues" = red
Related Skills
Harness Engineering Practice
Harness Engineering — a practical guide to the platform layer of coding agents (Claude Code & Codex): skills,
Docs Ia
Determines which tab and section a new documentation page belongs in. Use when adding new pages, reorganizing
Fable
Shortcut for claude-review with a single Fable Skeptic (deep behavioral reasoning, pinned to fable). Ignores t