Get a summary of all tasks by status Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster.
AI agents call task_summary to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
task_summary retrieves and summarizes task status information from persistent storage. No creation, modification, deletion, or code execution is involved. This is a straightforward Read operation with minimal risk—an AI agent misusing it can only access task metadata, not affect system state or data integrity.
From the tool's definition Tool description explicitly states 'Get a summary of all tasks by status' — a read-only query operation. The rationale mentions it retrieves data from .swarm/memory.db for analytics and tracking, with no write, delete, or execution capabilities described.
Attacks that exploit this kind of access
Get a summary of all tasks by status Use when native TodoWrite is wrong because you need cross-session task persistence, agent assignment, dependency tracking, or completion analytics in the .swarm/memory.db. For in-session checklists native TodoWrite is simpler and faster. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for task_summary: 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.
task_summary 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 task_summary 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 task_summary. 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.
task_summary 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.