Medium Risk

createPlan

Create .claude-plan.md in workspace root. Markdown with sections and task checklists.

How to control createPlan ↓

What createPlan does on Patchwork Os

AI agents use createPlan to create or update resources in Patchwork Os — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Patchwork Os environment.

Medium Risk

Why createPlan needs a policy

The tool creates or modifies a markdown planning file in the workspace root directory. This is a write operation (creates or modifies data reversibly) rather than read-only, as it creates new files. However, it does not delete, overwrite existing data irreversibly, move money, or execute arbitrary code—it only produces a markdown document for planning purposes.

From the tool's definition Tool name and description: "Create .claude-plan.md in workspace root. Markdown with sections and task checklists." This performs creation and modification of a file (.claude-plan.md) within the workspace, which is a reversible write operation.

Risk signalsAdmin/system-level operation

Documented attack patterns abuse exactly the kind of access createPlan gives an agent:

How to control createPlan

PolicyLayer is an MCP gateway — it sits between your AI agents and Patchwork Os, and nothing reaches the server without passing your rules. This is the rule we recommend for createPlan:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "createPlan": {
      "limits": [
        {
          "counter": "createplan_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

createPlan 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.

  1. Create a free account and register Patchwork Os — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about createPlan

What does the createPlan tool do? +

Create .claude-plan.md in workspace root. Markdown with sections and task checklists. It is categorised as a Write tool in the Patchwork Os MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on createPlan? +

Register the Patchwork Os MCP server in PolicyLayer and add a rule for createPlan: 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 Patchwork Os. Nothing to install.

What risk level is createPlan? +

createPlan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit createPlan? +

Yes. Add a rate_limit block to the createPlan 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.

How do I block createPlan completely? +

Set action: deny in the PolicyLayer policy for createPlan. 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.

What MCP server provides createPlan? +

createPlan is provided by the Patchwork Os MCP server (oolab-labs/patchwork-os). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Patchwork Os tool call.

Start from Patchwork Os, 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.

11 Patchwork Os tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.