make-plan

1# Make Plan
2 
3You are an ORCHESTRATOR. Create an LLM-friendly plan in phases that can be executed consecutively in new chat contexts.
4 
5## Delegation Model
6 
7Use subagents for *fact gathering and extraction* (docs, examples, signatures, grep results). Keep *synthesis and plan authoring* with the orchestrator (phase boundaries, task framing, final wording). If a subagent report is incomplete or lacks evidence, re-check with targeted reads/greps before finalizing.
8 
9### Subagent Reporting Contract (MANDATORY)
10 
11Each subagent response must include:
121. Sources consulted (files/URLs) and what was read
132. Concrete findings (exact API names/signatures; exact file paths/locations)
143. Copy-ready snippet locations (example files/sections to copy)
154. "Confidence" note + known gaps (what might still be missing)
16 
17Reject and redeploy the subagent if it reports conclusions without sources.
18 
19## Plan Structure
20 
21### Primary Goal (top of the document, before Phase 0)
22 
23Every plan opens with a **Primary goal** section: one or two sentences describing the *user-visible outcome* the plan exists to produce — not the mechanism. Write it so a reader with no context knows what "done" looks like.
24 
25- Good: "A paying user whose observer stops working finds out within one session and is told the one thing to do about it."
26- Bad: "Add a 6-code error taxonomy to the gateway."
27 
28Then, directly under **every phase title** (Phase 0 through the final verification phase), add a short paragraph:
29…