Back to Details

efficient-fable

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Efficient Fable

高效使用Fable

Use Claude Fable as the orchestrator, architect, synthesizer, and final judge. Use cheaper subagents for token-heavy research, coding, testing, and summarization that do not require Fable's full judgment.
将Claude Fable用作编排者、架构师、整合者和最终决策者。 让更廉价的子代理处理token消耗量大的研究、编码、测试和总结工作——这些工作不需要Fable的完整决策能力。

Where Fable Shines

Fable的优势场景

Reserve Fable for:
  • Decomposing ambiguous work into clean parallel slices.
  • Architecture, product, and safety tradeoffs.
  • Reading conflicting subagent reports and deciding what matters.
  • Integrating partial implementations into one coherent plan.
  • Final review, risk assessment, and user-facing synthesis.
将Fable保留用于以下场景：
  • 将模糊的工作拆解为清晰的可并行处理模块。
  • 架构、产品和安全层面的权衡决策。
  • 阅读子代理的冲突报告并判断关键信息。
  • 将部分实现整合为一个连贯的计划。
  • 最终审查、风险评估及面向用户的内容整合。

Delegation Pattern

任务委派模式

  1. Name the expensive-token risk: large repo search, long logs, broad docs, or repetitive edits.
  2. Split independent work into subagents before reading everything yourself.
  3. Use cheaper models for research scans, inventory, search summaries, narrow bug hunts, browser/testing passes, test output reduction, and bounded code edits.
  4. Ask subagents for concise evidence: files, line references, commands run, diffs, uncertainties, and stop conditions they hit.
  5. Spend Fable tokens on the decision layer: compare results, resolve conflicts, choose the implementation path, and review the final patch.
Prefer parallel subagents when the slices do not depend on each other. Keep blocking or highly coupled work local.
  1. 明确高token消耗风险：大型仓库搜索、冗长日志、宽泛文档或重复编辑操作。
  2. 在自行处理所有内容之前，将独立工作拆分给子代理。
  3. 使用更廉价的模型处理研究扫描、资源盘点、搜索总结、针对性漏洞排查、浏览器/测试执行、测试输出精简及限定范围的代码编辑。
  4. 要求子代理提供简洁的证据：文件、行号引用、执行的命令、差异内容、不确定点以及遇到的终止条件。
  5. 将Fable的token消耗用在决策层：对比结果、解决冲突、选择实现路径并审查最终补丁。
当任务模块之间互不依赖时，优先使用并行子代理。需要阻塞或高度耦合的工作则由Fable自行处理。

Handoff Packets

任务交接包

Write delegated prompts as if the subagent has no useful chat context. Include only the context it needs:
  • The repo path and exact objective.
  • The files, packages, or surfaces in scope and anything explicitly out of scope.
  • The evidence format to return: files, line refs, commands, diffs, failures, screenshots, and uncertainty.
  • The verification commands or browser flows to run, plus what success should look like when that is knowable.
  • Stop conditions: if the code does not match the prompt, a command fails after a reasonable retry, or the task needs out-of-scope files, stop and report instead of improvising.
撰写委派提示时，假设子代理没有可用的聊天上下文。仅包含其所需的必要信息：
  • 仓库路径和明确目标。
  • 范围内的文件、包或操作面，以及明确排除在外的内容。
  • 需返回的证据格式：文件、行号引用、命令、差异、失败信息、截图及不确定点。
  • 需执行的验证命令或浏览器流程，以及已知情况下成功的判定标准。
  • 终止条件：如果代码与提示不符、命令在合理重试后仍失败，或任务需要超出范围的文件，应停止操作并报告，而非自行发挥。

Vetting Delegated Work

委派工作的审核

Treat subagent reports as leads, not facts. Before using a high-impact finding, opening a PR, or telling the user the work is done, Fable should reopen the important cited files, confirm the relevant line refs or failures, and review the final diff against the task. Let lighter agents gather signal; keep truth-judgment with Fable.
将子代理的报告视为线索而非事实。在采用高影响的发现、提交PR或告知用户工作完成之前，Fable应重新打开重要的引用文件，确认相关行号引用或失败情况，并对照任务要求审查最终差异内容。让轻量代理收集信息，将事实判断保留给Fable。

Common Scenarios

常见场景

Treat these as soft defaults, not rigid rules:
  • Research: ask lighter agents to scan docs, prior art, APIs, and repo surfaces; Fable decides what evidence changes the plan.
  • Coding: give cheaper agents bounded edits or candidate patches; Fable owns shared-file coordination, integration, and final review.
  • Testing: have Fable suggest the validation direction and the scripts or browser checks that matter. Let lighter agents run targeted tests, browser flows, screenshots, and log reduction, then report exact commands, failures, likely causes, and whether failures look flaky, environmental, or real.
  • Debugging: use cheaper agents to cluster logs, reproduce issues, and try small fixes; Fable decides which diagnosis is most trustworthy.
If a task is tiny or the validation itself needs delicate judgment, keep it with Fable.
将这些视为灵活的默认规则，而非硬性规定：
  • 研究：让轻量代理扫描文档、已有成果、API和仓库表层内容；由Fable决定哪些证据会影响计划。
  • 编码：让更廉价的代理处理限定范围的编辑或候选补丁；Fable负责共享文件的协调、整合及最终审查。
  • 测试：由Fable提出验证方向及重要的脚本或浏览器检查项。让轻量代理执行针对性测试、浏览器流程、截图及日志精简，然后报告确切的命令、失败信息、可能原因，以及失败是否属于偶发、环境问题或真实故障。
  • 调试：使用更廉价的代理对日志进行聚类、复现问题并尝试小修复；由Fable判断哪种诊断结果最可信。
如果任务规模极小，或验证工作本身需要精细的判断，则仍由Fable处理。

Diagram

示意图

Use 
assets/fable-orchestrator.excalidraw
when a visual explanation helps.
如需可视化说明，可使用
assets/fable-orchestrator.excalidraw
。

Claims

效果说明

For codebase-heavy work, it is reasonable to describe this as up to 3-5x more cost-efficient and 2-4x faster when independent research, coding, or testing slices can run in parallel. Treat those as workload-dependent estimates, not guarantees.
Good launch copy:
Make Claude Fable more efficient by using cheaper subagents for token-heavy research, coding, and testing, saving Fable for judgment, architecture, synthesis, and final review.
对于代码库密集型工作，在可并行处理独立的研究、编码或测试模块时，这种方式的成本效率可提升3-5倍，速度可提升2-4倍。这些是基于工作负载的估算，而非保证值。
推荐的推广文案：
通过让更廉价的子代理处理token消耗量大的研究、编码和测试工作，将Claude Fable用于决策、架构、整合及最终审查，从而提升Claude Fable的使用效率。