# Docs How the tool works, as opposed to how to set it up. The [guides](https://agentchaperone.dev/guides) cover the setup; these are the documents the guides point to when a question needs the exact behavior. Each one is written and reviewed in [the repository](https://github.com/agent-chaperone/agent-chaperone), next to the code it describes, and copied here with only its links changed. Every change to this site is checked against the repository's main branch, and a copy that differs from it fails the check. ## The documents - **[Design](https://agentchaperone.dev/docs/design)** The architecture, each screen and the exact questions it asks, how a decision is made from the answers, the policy file, the audit log, and what content leaves the machine. - **[Screening a client’s own tools](https://agentchaperone.dev/docs/hooks)** Screening a client's own shell, file edits and fetches: the configuration, what each hook command answers, how a withheld result keeps the shape a tool returns, and what hooks cannot see. - **[Screening benchmark](https://agentchaperone.dev/docs/benchmark)** The public datasets and hand-labeled tool calls the questions were measured against, the recorded model responses, the limits of the numbers, and how to reproduce them without a key. ## In the repository only - **[Decision records](https://github.com/agent-chaperone/agent-chaperone/tree/main/docs/adr)** Why the main choices went the way they did, one record per decision. - **[Roadmap](https://github.com/agent-chaperone/agent-chaperone/blob/main/ROADMAP.md)** What each version shipped, and what the next one is for. - **[Security policy](https://github.com/agent-chaperone/agent-chaperone/blob/main/SECURITY.md)** How to report a vulnerability, and the security considerations for running it. --- Source: https://agentchaperone.dev/docs The reference documents for agent-chaperone: the design, the hooks adapter and the benchmark method, copied from the repository and kept identical to it.