goal-testlisted

Local sandbox for experimenting with Claude Code's /goal command (stop-hook condition + LLM-evaluator driving autonomous work toward a verifiable end state) applied to LETS workflows. Use when the user says "goal test", "goal-test", "test the goal skill", "stop hook experiment", "автономна задача", "long-running goal", or wants to design a /goal contract that chains /lets:* commands (plan → execute → check → commit → done) toward a defined termination. Local-only — not part of the lets plugin payload. For periodic polling/babysitting, use sibling skill `loop-test` (which covers /loop).
restarter/lets-workflow · ★ 6 · AI & Automation · score 75

Install: claude install-skill restarter/lets-workflow

# goal-test (local experiment) `/goal` installs a **session-scoped Stop hook with an LLM-evaluated termination condition**. After every model turn, an evaluator-LLM reads the transcript and judges whether the goal is met. If not, the turn is rejected and the model must keep working. Best fit: convergent autonomous work (drive a task / epic / PR to a defined end state). **Not for periodic polling** — that's `/loop`'s job (see `loop-test` skill). ## How `/goal` actually works Sources: `claude` binary v2.1.150 strings + official docs ([code.claude.com/docs/en/goal](https://code.claude.com/docs/en/goal)) + community write-ups (see References). ### Mechanics 1. User runs `/goal <condition>`. Stored as session-scoped state. **Cap: 4000 characters** per condition. 2. After every model turn (assistant message that would normally yield), evaluator-LLM is invoked with the condition + transcript. - **Evaluator runs on your configured "small fast model"** (Haiku by default). Eval tokens are billed separately; Anthropic describes them as "typically negligible" but they accumulate on long runs. - Evaluator reads the **transcript only** — assistant text + user messages. Tool inputs/outputs ARE in transcript, but you must surface evidence in your assistant text for the evaluator to weight it heavily. "Quote specific text from transcript whenever possible" is in its system prompt. 3. Evaluator returns JSON: - `{"ok": true, "reason": "<quote evidence>"}` → goal achieved, session