delegation-templates

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Delegation Prompt Templates

委托提示模板

Fill every

{blank}

. Delete a line only if truly inapplicable — never skip the ACCEPTANCE or REPORT sections. A delegation without objective acceptance criteria is a guess you outsourced.

REFERENCES (optional, prefer when they exist): paths to code, tests, rubrics, or HTML/specs that DEFINE done — a rich reference beats prose restating it. Add a

REFERENCES:

line to any template below when the task has one.

For non-trivial work, add these filled lines before ACCEPTANCE:

BUDGET:

{max turns/time/tokens}

. Stop at

{stop condition}

; escalate on

{escalation condition}

. EXCLUDED PATHS:

{attempted or ruled-out approaches + evidence}

. MAIN VERIFICATION:

{fresh evidence the delegator must reproduce before accepting done}

Common footer — include in EVERY delegation:

REPORT: return ONLY short conclusion bullets +
file:line
per claim + verification evidence if you changed anything. Hard cap 30 lines. Long artifacts → write to
{artifact_path}
and return the path. Do not paste file contents or logs. If you cannot meet an acceptance criterion, say which one and why — do not fake it.

填写所有

{blank}

占位符。仅当某一行确实不适用时才可删除——绝对不能跳过ACCEPTANCE（验收标准）或REPORT（报告）部分。缺乏客观验收标准的委托，本质上是把猜测外包了出去。

参考资料（可选，如有则优先提供）：定义任务完成状态的代码、测试、评分标准或HTML/规范文件路径——详实的参考资料远胜于文字复述。当任务有参考资料时，在下方任意模板中添加

REFERENCES:

行。

对于非琐碎工作，在ACCEPTANCE前添加以下已填写的内容：

BUDGET:
{max turns/time/tokens}
. 当达到
{stop condition}
时停止；当出现
{escalation condition}
时升级处理。 EXCLUDED PATHS:
{attempted or ruled-out approaches + evidence}
. MAIN VERIFICATION:
{fresh evidence the delegator must reproduce before accepting done}
.

通用页脚——所有委托都必须包含：

REPORT: 仅返回简短结论要点 + 每个声明对应的
file:line
+ 若有修改则附上验证证据。严格限制在30行以内。大型工件→写入
{artifact_path}
并返回路径。请勿粘贴文件内容或日志。若无法满足某条验收标准，请说明具体是哪一条及原因——切勿造假。

1. SEARCH / LOCATE (cheapest capable tier; read-only agent type if available)

1. SEARCH / LOCATE （成本最低的胜任层级；若有可用的只读Agent类型则优先使用）

GOAL: Find {what} in {repo/dir}. This will be used to {why}.
SCOPE: Look in {paths/globs}; also consider {alternative naming/conventions}.
ACCEPTANCE:
- Every match listed as file:line with a one-line role description.
- Explicitly state "no other occurrences" only after checking {N} naming variants: {variants}.
- Zero-result duty: before reporting zero matches, prove each search pattern works on a known positive (or synthetic sample); an unproven zero = UNCONFIRMED, not zero.
NON-GOALS: Do not review quality, do not propose fixes.

GOAL: Find {what} in {repo/dir}. This will be used to {why}.
SCOPE: Look in {paths/globs}; also consider {alternative naming/conventions}.
ACCEPTANCE:
- Every match listed as file:line with a one-line role description.
- Explicitly state "no other occurrences" only after checking {N} naming variants: {variants}.
- Zero-result duty: before reporting zero matches, prove each search pattern works on a known positive (or synthetic sample); an unproven zero = UNCONFIRMED, not zero.
NON-GOALS: Do not review quality, do not propose fixes.

2. IMPLEMENT (default worker tier)

2. IMPLEMENT （默认工作者层级）

GOAL: Implement {feature/change} in {files/module}. Motivation: {why}.
CONTEXT: {key constraints, existing helpers to reuse, style notes}. Read {files} first.
ACCEPTANCE:
- {objective condition, e.g. "`{test command}` exits 0"}.
- {behavioral condition, e.g. "endpoint returns 403 for expired tokens"}.
- No placeholder text; new non-trivial logic ships with one runnable check.
- Surgical diff: nothing outside {scope} touched.
VERIFY BEFORE REPORTING: run {command}; include exit code + key lines in the report.

GOAL: Implement {feature/change} in {files/module}. Motivation: {why}.
CONTEXT: {key constraints, existing helpers to reuse, style notes}. Read {files} first.
ACCEPTANCE:
- {objective condition, e.g. "`{test command}` exits 0"}.
- {behavioral condition, e.g. "endpoint returns 403 for expired tokens"}.
- No placeholder text; new non-trivial logic ships with one runnable check.
- Surgical diff: nothing outside {scope} touched.
VERIFY BEFORE REPORTING: run {command}; include exit code + key lines in the report.

3. REFACTOR (default worker tier)

3. REFACTOR （默认工作者层级）

GOAL: Refactor {target} to {shape}, behavior UNCHANGED. Motivation: {why}.
BASELINE FIRST: run {test command} before touching anything; record the result.
ACCEPTANCE:
- Same test results after as before (attach both).
- Public API/signatures unchanged unless listed here: {allowed changes}.
- No new dependencies; dead code your change created is removed.
STOP CONDITION: if behavior must change to proceed, stop and report — do not decide alone.

GOAL: Refactor {target} to {shape}, behavior UNCHANGED. Motivation: {why}.
BASELINE FIRST: run {test command} before touching anything; record the result.
ACCEPTANCE:
- Same test results after as before (attach both).
- Public API/signatures unchanged unless listed here: {allowed changes}.
- No new dependencies; dead code your change created is removed.
STOP CONDITION: if behavior must change to proceed, stop and report — do not decide alone.

4. RESEARCH (default worker tier)

4. RESEARCH （默认工作者层级）

GOAL: Answer: {question}. The answer will drive {decision}.
SOURCES: prefer {official docs/repo/spec}; treat blogs/forums as secondary.
ACCEPTANCE:
- Every claim cited (URL or file:line). Uncited = label UNCONFIRMED.
- Distinguish "documented" vs "inferred" vs "not found".
- "Not found" duty: prove each search pattern/query works on a known positive before reporting absence; an unproven "not found" = UNCONFIRMED.
- If sources conflict, present both sides — do not silently pick one.
OUTPUT: findings to {artifact_path}; return path + a ≤10-bullet summary.

GOAL: Answer: {question}. The answer will drive {decision}.
SOURCES: prefer {official docs/repo/spec}; treat blogs/forums as secondary.
ACCEPTANCE:
- Every claim cited (URL or file:line). Uncited = label UNCONFIRMED.
- Distinguish "documented" vs "inferred" vs "not found".
- "Not found" duty: prove each search pattern/query works on a known positive before reporting absence; an unproven "not found" = UNCONFIRMED.
- If sources conflict, present both sides — do not silently pick one.
OUTPUT: findings to {artifact_path}; return path + a ≤10-bullet summary.

5. REVIEW / VERIFY (fresh context; stronger tier when the change is risky; NEVER the author)

5. REVIEW / VERIFY （全新上下文；当变更存在风险时使用更高级层级；绝对不能是作者本人）

GOAL: Adversarially review {diff/files/claim}. Assume it is broken until proven otherwise.
CHECK:
- Claims vs reality: for each stated behavior, find the code or run the command that proves it.
- {task-specific checks: edge cases, error paths, security, contradictions between docs}.
- Files: read back in full; flag truncation, placeholders, broken paths/references.
ACCEPTANCE:
- Verdict per item: PASS / FAIL / UNCONFIRMED + one-line reason + file:line.
- Overall verdict on the last line, exactly one of: VERDICT: PASS | VERDICT: BLOCK.
Do not fix anything; report only.

GOAL: Adversarially review {diff/files/claim}. Assume it is broken until proven otherwise.
CHECK:
- Claims vs reality: for each stated behavior, find the code or run the command that proves it.
- {task-specific checks: edge cases, error paths, security, contradictions between docs}.
- Files: read back in full; flag truncation, placeholders, broken paths/references.
ACCEPTANCE:
- Verdict per item: PASS / FAIL / UNCONFIRMED + one-line reason + file:line.
- Overall verdict on the last line, exactly one of: VERDICT: PASS | VERDICT: BLOCK.
Do not fix anything; report only.

Dispatch shape A — in-process subagent (Agent tool)

调度格式A — 进程内子Agent（Agent工具）

Agent({
  subagent_type: "Explore" | "general-purpose" | ...,
  model: "sonnet" | "opus",   // cheapest tier that can pass ACCEPTANCE (haiku retired 2026-08-01; former haiku roles = sonnet at effort low)
  description: "{3-5 words}",
  prompt: "{filled template + common footer}"
})

Parallelize independent delegations in one message. Wait for results before dispatching anything that depends on them.

Agent({
  subagent_type: "Explore" | "general-purpose" | ...,
  model: "sonnet" | "opus",   // cheapest tier that can pass ACCEPTANCE (haiku retired 2026-08-01; former haiku roles = sonnet at effort low)
  description: "{3-5 words}",
  prompt: "{filled template + common footer}"
})

可在一条消息中并行处理独立的委托任务。在调度依赖于这些结果的任务之前，需等待所有结果返回。

Dispatch shape B — tmux worker (agent-tmux <cli>)

调度格式B — tmux工作者（agent-tmux <cli>）

agent-tmux claude assign {safe-name} {repo-dir} {prompt-file}

When the delegate is a tmux worker, ADD these lines to the filled template (they replace nothing — the common footer still applies):

Do not spawn additional tmux sessions or delegate further. When done, write the structured completion (result.json contract, schema_version 1) to the literal result path injected into this prompt — do not rely on
$TMUX_AGENT_RESULT
inside tool sandboxes. Put the REPORT bullets in its
summary
field. If the dispatcher gives an overall deadline, write that valid result at least 120 seconds before it; an artifact without it remains UNCONFIRMED.

Write the filled template to a prompt file and pass its path to

assign

— never interpolate raw task text into the command line.

assign

owns start, submission, supervision, canonical-result validation, and stop; do not hand-chain them. Ownership boundaries: this skill owns the prompt body (templates + footers + addendum). The dispatch shapes above are illustrative carriers showing where the filled prompt lands — the authoritative rules for deciding WHETHER to delegate, constructing invocations, and supervising workers after launch live in the tmux-delegate agent and the tmux-agent-tools skill, and are not restated here.

agent-tmux claude assign {safe-name} {repo-dir} {prompt-file}

当委托对象是tmux工作者时，需在已填写的模板中添加以下内容（无需替换任何内容——通用页脚仍然适用）：

Do not spawn additional tmux sessions or delegate further. When done, write the structured completion (result.json contract, schema_version 1) to the literal result path injected into this prompt — do not rely on
$TMUX_AGENT_RESULT
inside tool sandboxes. Put the REPORT bullets in its
summary
field. If the dispatcher gives an overall deadline, write that valid result at least 120 seconds before it; an artifact without it remains UNCONFIRMED.

将已填写的模板写入提示文件，并将其路径传递给

assign

命令——切勿将原始任务文本直接插入命令行。

assign

命令负责启动、提交、监控、验证标准结果和停止任务；请勿手动链式调用这些操作。所有权边界：本skill负责提示内容（模板+页脚+补充内容）。上述调度格式仅为展示提示内容最终位置的示例载体；关于是否委托、构建调用、启动工作者后监控的权威规则，请查看tmux-delegate agent和tmux-agent-tools skill，此处不再赘述。