A way to help Claude Code follow rules during a session
This is an advanced workflow for reducing cases where Claude Code agents ignore set rules or behave in unexpected ways. It uses a tool called sentience-governor to show the agent’s operating record inside the Claude Code session. That record can include policy violations, intent that was not clearly declared, and advisory flags. The operator can bring this record into view with specific slash commands. Once the governance information is visible in the session, the agent may use it to correct its own behavior. The workflow is presented as useful for quality control, token saving, context and memory work, debugging, shipping, skills, and MCP-related setups.
Key points
- The workflow aims to help Claude Code agents follow defined policies more consistently.
- sentience-governor shows policy violations, undeclared intent, and advisory flags inside the session.
- Specific slash commands are used to bring the governance record into the working context.
- Making that record visible may help the agent correct its own behavior.
- The workflow is aimed at advanced use cases such as quality control, token saving, debugging, and MCP setups.
Quick term guide
- tool call
- One time an AI agent uses a tool, such as search, calculation, or file reading.
- sentience-governor
- The tool named in the post for showing an AI agent’s rule-following record.
- slash commands
- Short commands that start with / inside an AI tool.
- governance
- The policies and controls a company uses to manage data and systems safely and in compliance with rules.
- debugging
- The process of finding and fixing the cause of errors or unexpected behavior in code.
- visibility
- How easily people can discover and notice a product.
- coding sessions
- Past periods of work where code was written, changed, or discussed.
- use cases
- Use cases are simple examples of what a tool can be used for.