agenticow — show what a branch changed relative to its lineage: {added, overridden, deleted} vector-id lists. Use when you are about to promote and want to preview the exact merge, or when auditing what a branch actually wrote. Diffing by re-querying is wrong because deletions (tombstones) are in...
AI agents call agenticow_diff to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and computes a diff between a branch and its lineage, surfacing added/overridden/deleted vector IDs. It does not perform any writes, deletions, or executions — it is purely an inspection/audit tool. Severity is low since it only reads metadata about changes without modifying anything.
From the tool's definition show what a branch changed relative to its lineage: {added, overridden, deleted} vector-id lists... preview the exact merge... auditing what a branch actually wrote
Attacks that exploit this kind of access
agenticow — show what a branch changed relative to its lineage: {added, overridden, deleted} vector-id lists. Use when you are about to promote and want to preview the exact merge, or when auditing what a branch actually wrote. Diffing by re-querying is wrong because deletions (tombstones) are invisible to a read — diff() surfaces them explicitly. Requires the branch was opened with edit tracking (default on). It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for agenticow_diff: 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.
agenticow_diff is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the agenticow_diff 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.
Set action: deny in the PolicyLayer policy for agenticow_diff. 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.
agenticow_diff 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.
agenticow_diff 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 →