Claude Code Bare Harness
waynehacking8/claude-code-bare-harness
Strip Claude Code harness para testes A/B de comportamento do modelo
Ver no GitHubAgent para testes A/B que remove camadas da instrução do Claude Code, permitindo observar o comportamento do modelo com injeção mínima de contexto. Útil para pesquisa de como o harness afeta estilo e resposta, mantendo os limites de segurança do modelo intactos.
Instalação
npx convez-ai waynehacking8/claude-code-bare-harness1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- A/B testing: comparar respostas com e sem agent harness
- Pesquisa de comportamento: estudar como instruções afetam saída do modelo
- Transparency research: entender camadas de injeção no Claude Code
Veredito

Ferramenta honesta e bem documentada para pesquisa reproducível, com posicionamento claro sobre o que pode e não pode remover. Ideal para engenheiros que estudam behavior modeling e querem isolar variáveis no Claude Code.
README
A tradução para o português deste README ainda está na fila.
Minimizing the Claude Code Harness for Model-Behavior Testing
Purpose: When observing model behavior or running A/B tests, strip as much of the Claude Code agent harness as possible so that what reaches the model is closer to "just the user message."
⚠️ Read this first This documents removing the agent-instruction layer, NOT "disabling safety."
- The model's safety behavior comes from training (weights), not the system prompt. No CLI flag can remove it.
- The server-side content safety classifier cannot be disabled via local config.
- After
--system-prompt ""you still get the same Claude with the same safety boundaries — just without the tool definitions, CLAUDE.md, and behavior rules. Treat this as a "minimal harness," not a "bare/unrestricted model."
1. Background: what actually gets injected per request
Before sending your message, Claude Code stacks several context layers:
- Built-in system prompt — agent identity, behavior rules, output style
- Tool definitions (schema) — JSON schemas for Bash / Read / Edit / …
- Setting sources —
~/.claude/settings.json,CLAUDE.md, auto-memory - Dynamic blocks — cwd, git status, OS, date (system-reminder)
- Model training — baked into weights, NOT visible/removable here
2. What each flag removes
| Flag | Removes | Layer |
|---|---|---|
--system-prompt "" | Built-in Claude Code agent instructions | system prompt |
--setting-sources "" | CLAUDE.md / memory / settings injection | conversation injection |
--tools "" | Tool schemas | tool definitions |
| clean cwd | Avoids triggering auto-memory | conversation injection |
--append-system-prompt | (adds instead of replacing — for reference) | system prompt |
3. Minimal-harness invocation
mkdir -p /tmp/bare-test && cd /tmp/bare-test # clean cwd -> no memory
claude --system-prompt "" --tools "" --setting-sources "" "your prompt"
# one-shot:
claude -p --system-prompt "" --tools "" --setting-sources "" "your prompt"
4. Residuals you CANNOT remove (subscription/OAuth CLI)
- One SDK identity line:
You are a Claude agent, built on Anthropic's Claude Agent SDK. - A system-reminder containing user email + current date
- The model's safety training — not in the system prompt, not removable by any flag
- The server-side safety classifier — not disableable via local config
5. Scope / honest positioning
- Good for: A/B tests (harness vs. no-harness response diffs), studying how the harness affects style and behavior, transparency/research.
- Not for: "removing safety limits" — it does not and cannot do that.
- A truly zero-injection setup (no SDK identity line) only exists via the raw API
with no
systemparameter; that's a separate path and still subject to the same model-level safety.