swarm_pheromone_update
Record a normalized per-agent task outcome for a running pheromone-adaptive swarm. Use when a static agent pool is wrong because repeated task evidence should update role-aware EMA fitness and produce a bounded keep/suspend/reactivate decision; native Task has no persistent swarm eligibility gate.
This record as markdown: /tools/io-github-ruvnet-claude-flow/swarm-pheromone-update.md
What swarm_pheromone_update does on Claude Flow
AI agents use swarm_pheromone_update to create or update resources in Claude Flow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.
Why swarm_pheromone_update is rated Medium
This tool writes to swarm agent state and fitness metrics, causing state mutations that affect which agents are active. It updates EMA (exponential moving average) fitness scores and produces membership decisions (keep/suspend/reactivate), making it a Write operation. It is not Destructive because fitness updates and role suspensions are conceptually reversible or can be overridden by subsequent updates.
From the tool's definition Tool description: 'Record a normalized per-agent task outcome... should update role-aware EMA fitness and produce a bounded keep/suspend/reactivate decision.' The verb 'update' and 'record' indicate modification of persistent state (agent fitness metrics,…
Attacks that exploit this kind of access
The rule that runs swarm_pheromone_update 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 swarm_pheromone_update, this is the rule to start with:
swarm_pheromone_update stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every swarm_pheromone_update call is checked against it from then on.
Questions about swarm_pheromone_update
Record a normalized per-agent task outcome for a running pheromone-adaptive swarm. Use when a static agent pool is wrong because repeated task evidence should update role-aware EMA fitness and produce a bounded keep/suspend/reactivate decision; native Task has no persistent swarm eligibility gate. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Flow MCP server in PolicyLayer and add a rule for swarm_pheromone_update: 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.
swarm_pheromone_update 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 swarm_pheromone_update 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 swarm_pheromone_update. 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.
swarm_pheromone_update 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.
This server
Across the catalogue