Record a resume plan for work deferred past the rate-limit reset (use after fit_check says defer). Headroom shows a countdown in the HUD and flags the work as ready in prompt stamps once the window resets.
AI agents use plan_resume to create or update resources in Headroom — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Headroom environment.
This tool creates or modifies persisted data (a resume plan record and associated flags) rather than reading, executing code, destroying data, or moving money. The effect is reversible — plans can be updated or cleared. While the deferred work itself may later execute, plan_resume only records intentions.
From the tool's definition Tool description states it will 'Record a resume plan' and 'flags the work' — these are metadata creation and modification operations that persist state for later execution. The tool writes resume plan data to be retrieved after a rate-limit reset.
Attacks that exploit this kind of access
Record a resume plan for work deferred past the rate-limit reset (use after fit_check says defer). Headroom shows a countdown in the HUD and flags the work as ready in prompt stamps once the window resets. It is categorised as a Write tool in the Headroom MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Headroom MCP server in PolicyLayer and add a rule for plan_resume: 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 Headroom. Nothing to install.
plan_resume is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the plan_resume 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 plan_resume. 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.
plan_resume is provided by the Headroom MCP server (tyejcoleman/headroom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →