cursor-implementation-looplisted

Delegate implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).
olddonkey/olddonkey-skills · ★ 16 · Code & Development · score 78

Install: claude install-skill olddonkey/olddonkey-skills

# Cursor implementation loop **The implementer subagent writes the code; you own the judgment.** A delegated implementer is fast but it self-reports success, and pointing it at a long test suite wastes the machine you share with it. You give it a precise spec, then be the thing that actually verifies and ships. **This includes bug fixes**: a bug found at review, at the gate, or later is a unit like any other — you diagnose and spec, the implementer implements. Editing code directly "because it's faster" silently inverts the division of labor and costs review its independence. The loop: **decompose → dispatch → review → iterate → gate → publish → next**. Cursor-specific mechanics (subagent dispatch, resume, model pinning and its limits, enforcement gaps vs. hard sandboxes) live in [references/cursor-runtime.md](references/cursor-runtime.md); read it before the first dispatch of a session. ## Non-negotiables 1. **Review is mandatory and independent.** The implementer's summary is a claim; the diff is the evidence. Never skip review because it says it's done. 2. **An assumed default never leaves the machine.** With no explicit user choice, stop at the working tree — even a local commit can fire hooks/signing. Commit, push, PR, and merge each need the user to have said yes once for this repo, **asked at kickoff, not discovered at publish time**. **Once is once**: that authorization is per-repo, persists across sessions until revoked or the work changes c