SuperSkill

Overview Schema Source Related Servers Discussions Admin

prune

Destructive

Archive or delete stale vault content using configurable retention policies. Preview changes with a dry-run before removing old sessions or completed tasks.

Instructions

Archive or delete stale vault content based on retention policies. Use mode='dry-run' first to preview.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "prune"
  }
}

Input Schema

Name	Required	Description
`all`	No	Prune all projects
`mode`	No	Prune mode (default dry-run)
`project`	No	Project slug (or omit for auto-detect)
`sessions_days`	No	Session retention in days (default 30)
`workspace_path`	No	Absolute thread workspace directory; must map to this project. Omit only when the server cwd is the thread workspace.
`done_tasks_days`	No	Done task retention in days (default 30)

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.15.1Oct 15, 2026

addedInput schema / properties / done_tasks_days / minimum
```
Added value: +0
```
addedInput schema / properties / sessions_days / minimum
```
Added value: +0
```

addedInput schema / properties / workspace_path

Added value: +{
+  "description": "Absolute thread workspace directory; must map to this project. Omit only when the server cwd is the thread workspace.",
+  "type": "string"
+}

First observedv0.6.1Aug 10, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The destructiveHint=true annotation already flags the write/mutation risk, and the description adds useful context by disclosing that deletion is policy-driven and that a dry-run preview exists as a safeguard. It stops short of explaining irreversibility or what happens to archived vs deleted content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with the core action front-loaded and the safety tip second. No filler, nothing wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six optional parameters with full schema coverage, no output schema, and a destructive annotation, the description covers the essential risk and preview path. It could add a bit more on scope (project vs all) behavior, but an agent has enough to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters, including defaults and the mode enum, are already documented. The description only restates the dry-run mode value, adding no new semantics beyond the schema baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb pair (archive/delete) plus the resource (stale vault content) and the selection basis (retention policies). An agent knows what it does, though it doesn't differentiate itself from sibling maintenance tools like hygiene_report or worktree_gc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives one concrete workflow instruction: run mode='dry-run' first to preview. It does not state when pruning is appropriate versus alternatives, nor any prerequisites (e.g. permissions or project mapping) that would help an agent decide to invoke it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.