菜单
Use the Milknado MCP tools to decompose a goal into a Mikado-style change graph and produce a token-budgeted batch plan.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | milknado-plan |
| description | Use the Milknado MCP tools to decompose a goal into a Mikado-style change graph and produce a token-budgeted batch plan. |
| license | MIT |
| compatibility | Requires the milknado MCP server to be configured and running. |
| allowed-tools | ["read","mcp__milknado__milknado_graph_summary","mcp__milknado__milknado_add_node","mcp__milknado__milknado_plan_batches"] |
Use this skill to turn a high-level goal into a structured Mikado execution plan backed by the Milknado graph. The skill calls the Milknado MCP server to inspect the current graph state, decompose the goal into fine-grained changes, and persist each change as a graph node.
milknado_graph_summary to check for existing
nodes. If nodes exist, operate in resuming mode.id, path, edit_kind, description, symbols, and depends_on.milknado_plan_batches with the manifest to
confirm the solver produces a feasible batch plan.milknado_add_node for each change, linking
prerequisite relationships via parent_id.| Tool | Purpose |
|---|---|
milknado_graph_summary | Read the current graph (id, status, description per node). |
milknado_add_node | Add a new work node, optionally linked to a parent. |
milknado_plan_batches | Compute token-budgeted, precedence-respecting batches. |
{
"manifest_version": "milknado.plan.v2",
"goal": "Short goal statement",
"goal_summary": "What / why / success criteria (2–4 sentences).",
"changes": [
{
"id": "c1",
"path": "src/example.py",
"edit_kind": "modify",
"description": "Causal description referencing the goal.",
"symbols": [{"name": "ExampleClass", "file": "src/example.py"}],
"depends_on": []
}
]
}
Closed edit_kind values: add, modify, delete, rename
Staff Engineer code review orchestrator. Runs nine orthogonal LLM dimensions over a diff and emits a stake-weighted report plus hash-anchored sidecar JSON.
Finish what /age started. Loads both sidecars (fixes + suggestions), renders a unified stake table, gates on user approval, routes each approved item to the right handler (/cleanup or a cook sub-agent), then re-ages the touched paths up to a hard 3-turn cap.
Iterative thinking amplifier for fuzzy ideas. Routes input to the right starting mode (Explore, Ground, Shape, Sketch, Grill, Diagnose), runs Validate Cycles to anchor claims, locks down interfaces in pseudocode, and only curdles a spec (and optional issues) after a two-key handshake plus a coherence self-check.
Scan a codebase for custom code that duplicates what open-source libraries already do, then recommend which libraries to adopt. Detects hand-rolled utility functions, custom retry logic, manual validation, DIY date handling, home-grown argument parsers, and other reinvented wheels. Cross-checks against installed dependencies and open specs. Returns scored migration recommendations with effort estimates. Use when the user mentions reinventing the wheel, asks if there is a library for something they built, wants a build-vs-buy audit, asks "should we just use lodash for this", or wants to find dependency opportunities.
AST-aware code search using tilth MCP. Finds definitions first, then usages. Use tree-sitter structural matching instead of blind text grep. Understand dependencies and call graphs. Use when: finding where symbols are defined, tracing call chains, understanding code structure, finding all callers of a function. Do NOT use for reading files — use cheez-read. Do NOT use for editing — use cheez-write. Examples: "find where handleAuth is defined", "what calls validateToken?", "trace the ServeHTTP, HandlersChain, Next functions", "find all implementations of the UserService interface".
Mechanical apply of /age's hash-anchored sidecar fixes via tilth_edit. The cleanup-wolf sub-agent is the only LLM in the path, fired per anchor mismatch.