Agent Goal
Write one /goal line that a coding agent can keep pursuing until the transcript proves the work is done.
This skill owns the slash-goal artifact. Do not use it for ordinary prompt
drafting, handoffs, continuation prompts, delegation briefs, or prompt
engineering.
Shape
/goal <single objective> in <lane> until <observable evidence proves completion>. First read <starting context>. Work in checkpoints and surface <validation evidence> after each checkpoint.
Answer these in order, then compress them into one line:
What should change?
Where should the agent start?
What evidence proves it changed?
When should the agent stop?
Include only execution-critical detail:
- Objective: one concrete outcome, not a backlog of unrelated wishes.
- Lane: files, packages, apps, issues, specs, or the intended work area.
- Starting context: the first files, plans, logs, screenshots, or acceptance criteria to read.
- Evidence: command output, tests, build result, screenshot check, eval score, file count, or reviewed artifact.
- Stop condition: the exact transcript-visible state that means the goal is achieved.
Rules
- Start the answer with
/goal when the user asks for the goal text.
- Make completion judgeable by someone who can only read the transcript.
- Prefer exact checks over vague proof: "
bun test packages/account exits 0" beats "tests pass."
- Point long requirements at a file instead of pasting them into the goal.
- Ask for checkpoints when the work spans multiple turns.
- Bound repeated failure: after three failed attempts on the same check, report the root cause and next decision.
- Do not create a
/goal for vague wishes, open-ended research, unrelated chores, or work with no observable evidence.
Platform Note
Different agents may evaluate goals differently, but the portable rule is the
same: the goal should not rely on hidden state. Tell the agent to run checks and
surface evidence in the transcript.
Check
Before handing back a goal, verify:
- It has one main objective.
- It names where to start.
- It names the evidence that proves completion.
- It tells the agent to surface that evidence.
- It tells the agent when to stop.
1---2name: agent-goal3description: Draft a `/goal` line that gives long-running Codex or Claude Code work an objective, validation evidence, and a stop condition. Use when the user explicitly asks for `/goal`, an agent goal, or a completion condition.4metadata:5 source: https://skillmd.com/skills/epicenterhq/agent-goal6---78# Agent Goal910Write one `/goal` line that a coding agent can keep pursuing until the transcript proves the work is done.1112This skill owns the slash-goal artifact. Do not use it for ordinary prompt13drafting, handoffs, continuation prompts, delegation briefs, or prompt14engineering.1516## Shape1718```txt19/goal <single objective> in <lane> until <observable evidence proves completion>. First read <starting context>. Work in checkpoints and surface <validation evidence> after each checkpoint.20```2122Answer these in order, then compress them into one line:2324```txt25What should change?26Where should the agent start?27What evidence proves it changed?28When should the agent stop?29```3031Include only execution-critical detail:3233- Objective: one concrete outcome, not a backlog of unrelated wishes.34- Lane: files, packages, apps, issues, specs, or the intended work area.35- Starting context: the first files, plans, logs, screenshots, or acceptance criteria to read.36- Evidence: command output, tests, build result, screenshot check, eval score, file count, or reviewed artifact.37- Stop condition: the exact transcript-visible state that means the goal is achieved.3839## Rules40411. Start the answer with `/goal` when the user asks for the goal text.422. Make completion judgeable by someone who can only read the transcript.433. Prefer exact checks over vague proof: "`bun test packages/account` exits 0" beats "tests pass."444. Point long requirements at a file instead of pasting them into the goal.455. Ask for checkpoints when the work spans multiple turns.466. Bound repeated failure: after three failed attempts on the same check, report the root cause and next decision.477. Do not create a `/goal` for vague wishes, open-ended research, unrelated chores, or work with no observable evidence.4849## Platform Note5051Different agents may evaluate goals differently, but the portable rule is the52same: the goal should not rely on hidden state. Tell the agent to run checks and53surface evidence in the transcript.5455## Check5657Before handing back a goal, verify:5859- It has one main objective.60- It names where to start.61- It names the evidence that proves completion.62- It tells the agent to surface that evidence.63- It tells the agent when to stop.