/g The Contract Codex ← 返回动态 Catalog

Real CLI Goal Loop

Verify a real CLI goal loop where the second judge round confirms completion.

难度:intermediate 分类:goal-maintenance 来源:NousResearch/hermes-agent PR 18262

完整 Prompt(可直接复制)

/goal
GOAL:
Complete Real CLI Goal Loop for a goal-management workflow: Verify a real CLI goal loop where the second judge round confirms completion.

CONTEXT:
- Before editing, read the nearest AGENTS.md/CLAUDE.md, current issue or PLAN.md, and any failing logs already in the repo.
- Inspect active goals, done conditions, audit logs, and continuation state.
- Establish a baseline by running or locating evidence for: `live judge round-trip`.

CONSTRAINTS:
- Keep the scope limited to this goal; do not expand into unrelated cleanup.
- Do not weaken tests, delete assertions, or mask errors to make verification pass.
- Respect the repository's AGENTS.md/CLAUDE.md instructions and existing patterns.
- Do not mark a goal complete without auditing the current done condition.
- Keep goal edits and completion reasons visible in the final output.

DONE WHEN:
- The implementation or documentation directly satisfies: Verify a real CLI goal loop where the second judge round confirms completion.
- The verification command or evidence path succeeds: `live judge round-trip`.
- The final diff is scoped to the relevant files and has no unrelated formatting churn.

VERIFY:
- Run `live judge round-trip` or the closest repo-local equivalent if the exact command is not available.
- Capture before/after evidence for the behavior, metric, report, or artifact involved.
- If verification cannot run locally, stop and report the missing dependency instead of guessing success.

OUTPUT:
- Summarize changed files, key decisions, verification output, and remaining risks.
- Include any follow-up that is required for production rollout or human review.

STOP RULES:
- Pause if secrets, production access, stakeholder decisions, or destructive data operations are required.
- Pause after three failed fix attempts on the same symptom and challenge the root-cause hypothesis.
- Do not mark the goal complete until the current repository state has been audited against DONE WHEN.

来源与证据

原始来源: NousResearch/hermes-agent PR 18262

证据摘要: print hello, Ralph loop; source: NousResearch/hermes-agent PR 18262; type: github-pr; verification: live judge round-trip