Delete a VS Code .instructions.md file from the prompts directory.
AI agents call delete_instruction to permanently remove resources in Mode Manager MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes instruction files, which cannot be undone. Deletion is an irreversible operation that destroys data. While the blast radius is somewhat contained to instruction files rather than critical system data, unauthorized or accidental deletion of instructions could disrupt workflows, remove important prompt configurations, or require manual restoration.
From the tool's definition Tool name is 'delete_instruction' and description states it will 'Delete a VS Code .instructions.md file from the prompts directory.' The verb 'Delete' combined with file removal indicates irreversible data destruction.
Documented attack patterns abuse exactly the kind of access delete_instruction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mode Manager MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_instruction:
{
"version": "1",
"default": "deny",
"hide": [
"delete_instruction"
]
} delete_instruction disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a VS Code .instructions.md file from the prompts directory. It is categorised as a Destructive tool in the Mode Manager MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mode Manager MCP server in PolicyLayer and add a rule for delete_instruction: 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 Mode Manager MCP. Nothing to install.
delete_instruction 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 delete_instruction 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 delete_instruction. 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.
delete_instruction is provided by the Mode Manager MCP server (niclasolofsson/mode-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mode Manager MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Mode Manager MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.