agenticow_rollback
agenticow — discard all edits since the most recent checkpoint on an .rvf memory file. Reuses a fresh COW child derived from the checkpoint. Use when a Darwin tick or agent experiment regressed and you want to revert memory state without re-running. Deleting+rebuilding the .rvf is wrong because r...
This record as markdown: /tools/io-github-ruvnet-claude-flow/agenticow-rollback.md
What agenticow_rollback does on Claude Flow
AI agents call agenticow_rollback to permanently remove resources in Claude Flow, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why agenticow_rollback is rated Critical
The tool irreversibly discards all edits made since the last checkpoint, permanently losing data written after that point. While earlier history is preserved, the post-checkpoint edits are gone and cannot be recovered — this is a one-way destructive operation on memory state. The description itself warns that 'the data after the bad point is lost', confirming irreversibility.
From the tool's definition discard all edits since the most recent checkpoint on an .rvf memory file
Attacks that exploit this kind of access
The rule that runs agenticow_rollback safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agenticow_rollback, this is the rule to start with:
agenticow_rollback is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every agenticow_rollback call is checked against it from then on.
Questions about agenticow_rollback
agenticow — discard all edits since the most recent checkpoint on an .rvf memory file. Reuses a fresh COW child derived from the checkpoint. Use when a Darwin tick or agent experiment regressed and you want to revert memory state without re-running. Deleting+rebuilding the .rvf is wrong because rebuild cost is O(N) and the data after the bad point is lost; rollback is O(edits-since-checkpoint) and the earlier history stays intact via the lineage manifest. It is categorised as a Destructive tool in the Claude Flow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Flow MCP server in PolicyLayer and add a rule for agenticow_rollback: 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 Claude Flow. Nothing to install.
agenticow_rollback is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the agenticow_rollback 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_rollback. 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_rollback is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Flow, and thousands of servers like it.
Across the catalogue