loop-goal-engineeringlisted

This skill should be used when the user wants to author agentic loops or goal/completion conditions — "write a loop prompt", "loop engineering", "set up a ralph loop", "run Claude overnight", "write a /goal condition", "goal mode", "goal engineering", "stop condition for my agent", "completion criteria", "definition of done for the agent", "long-horizon task setup", "keep the agent working until", "make Codex run until tests pass", "PLANS.md", "harness for a long run", "my agent stops too early", "my agent never finishes", or wants Claude Code /loop, /goal, Stop hooks, or Codex Goal Mode set up well. Covers loop prompt authoring, goal condition design, the four-file long-horizon scaffold, and anti-reward-hacking hardening. For ordinary single-shot prompts, use prompt-engineering instead.
RadOrigin-LLC/RAD-Claude-Skills · ★ 5 · AI & Automation · score 73

Install: claude install-skill RadOrigin-LLC/RAD-Claude-Skills

# Loop & Goal Engineering Author the artifacts that drive autonomous agent runs: **loop prompts** (re-run cold each iteration until a backlog is done), **goal conditions** (machine- or evaluator-checkable completion criteria), and the **long-horizon file scaffold** that carries state between iterations. The runtime primitives exist — Claude Code `/goal` and `/loop`, Stop hooks, Codex Goal Mode, bash while-loops. They all assume the human can already write a good loop prompt or goal condition. That authoring step is this skill's job. --- ## Step 1 — Classify the Deliverable | User wants | Deliverable | Primary reference | |---|---|---| | Agent grinds through a backlog / overnight run | **Loop prompt** (+ scaffold files) | `references/loop-patterns.md` | | Agent keeps working until X is true | **Goal condition** | `references/goal-specs.md` | | Multi-hour/multi-day autonomous project | **Four-file scaffold** + loop prompt + goal | both | | A check that must gate with zero exceptions | **Stop-hook script spec** | goal-specs.md §2 | If the request is really a one-shot prompt with no iteration ("write a prompt that refactors this file"), hand off to the **prompt-engineering** skill. ## Step 2 — Pick the Harness Use the harness selection table in `references/loop-patterns.md` §1. Ask at most one question if the target runtime is ambiguous (Claude Code vs Codex vs raw bash loop) — it changes the output format: - **Claude Code `/goal`** → condition must be provable from the