Write the /goal finish line as an outcome plus success criteria built from evidence, not vibes, so the agent knows when it is truly done.
/goal GOAL: Complete Goal Finish Line Built From Evidence for a coding-agent workflow repository: Write the /goal finish line as an outcome plus success criteria built from evidence, not vibes, so the agent knows when it is truly done. CONTEXT: - Before editing, read the nearest AGENTS.md/CLAUDE.md, current issue or PLAN.md, and any failing logs already in the repo. - Inspect goal text, progress logs, branch state, and verification artifacts. - Establish a baseline by running or locating evidence for: `pytest && git diff --check`. 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 claim a goal is complete without a current audit of the stated contract. - Pause if the goal text, branch state, or permissions are inconsistent. DONE WHEN: - The implementation or documentation directly satisfies: Write the /goal finish line as an outcome plus success criteria built from evidence, not vibes, so the agent knows when it is truly done. - The verification command or evidence path succeeds: `pytest && git diff --check`. - The final diff is scoped to the relevant files and has no unrelated formatting churn. VERIFY: - Run `pytest && git diff --check` 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.
原始来源: How I Use /goal To Stop Babysitting AI Agents - aimaker (Substack)
证据摘要: A good finish line is built from evidence, not vibes.; source: How I Use /goal To Stop Babysitting AI Agents - aimaker (Substack); type: third-party-tutorial; verification: pytest && git diff --check