hooks_intelligence_trajectory-step

Record step in trajectory for reinforcement learning Use when native Bash hooks (via Claude Code\

Server Ruflo ruvnet/ruflo
Category Write
Risk class Medium
Parameters 00 required

What hooks_intelligence_trajectory-step does on Ruflo

AI agents use hooks_intelligence_trajectory-step to create or update resources in Ruflo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ruflo environment.

Why hooks_intelligence_trajectory-step needs a policy

The tool records (writes) a data point into a trajectory log used for reinforcement learning. This is a Write operation as it creates/appends data reversibly. It does not delete, execute code directly, or involve financial transactions. Severity is medium because misuse could corrupt RL training data or manipulate agent learning trajectories, but it is unlikely to cause immediate irreversible harm.

From the tool's definition 'Record step in trajectory for reinforcement learning' — the tool writes/persists a trajectory step entry into a data store for RL purposes

Questions about hooks_intelligence_trajectory-step

What does the hooks_intelligence_trajectory-step tool do? +

Record step in trajectory for reinforcement learning Use when native Bash hooks (via Claude Code\. It is categorised as a Write tool in the Ruflo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on hooks_intelligence_trajectory-step? +

Register the Ruflo MCP server in PolicyLayer and add a rule for hooks_intelligence_trajectory-step: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ruflo. Nothing to install.

What risk level is hooks_intelligence_trajectory-step? +

hooks_intelligence_trajectory-step is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit hooks_intelligence_trajectory-step? +

Yes. Add a rate_limit block to the hooks_intelligence_trajectory-step rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block hooks_intelligence_trajectory-step completely? +

Set action: deny in the PolicyLayer policy for hooks_intelligence_trajectory-step. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides hooks_intelligence_trajectory-step? +

hooks_intelligence_trajectory-step is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

hooks_intelligence_trajectory-step is one line of Ruflo's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.