token-budget-advisor
回答前先讓你選 25% 到 100% 的回應深度並估計 token
中文翻譯
--- name: token-budget-advisor description: 回答之前，先提供回應深度的選項（25%/50%/75%/100%）並附上 token 估計，再依選擇的層級回答。當使用者想控制回應長度或 token 預算時使用，例如 'token budget'、'short version'、'brief answer'、'respuesta corta vs larga'、'cuántos tokens'、'ahorrar tokens'、'responde al 50%'、'dame la versión corta'、'quiero controlar cuánto usas'。如果這個 session 已經設定過深度，或「token」指的是認證/付款 token，就跳過。 metadata: origin: community --- # Token Budget Advisor (TBA) 攔截回應流程，在 Claude 回答**之前**，讓使用者選擇回應的深度。 ## 何時使用 - 使用者想控制回應要多長或多詳細 - 使用者提到 token、預算、深度或回應長度 - 使用者說「short version」、「tldr」、「brief」、「al 25%」、「exhaustive」等等 - 任何使用者想事先選擇深度/細節層級的時候 **不要觸發**的情況：使用者在這個 session 已經設定過層級（默默維持它），或答案簡單到只有一行。 ## 運作方式 ### 步驟 1：估計輸入的 token 用 repo 標準的 context-budget 啟發式，在心裡估計 prompt 的 token 數。 使用跟 [context-budget](../context-budget/SKILL.md) 相同的校準指引： - 純文字：`words × 1.3` - 程式碼為主，或混合/程式碼區塊：`chars / 4` 混合內容就用佔多數的內容類型，並維持這是啟發式的估計。 ### 步驟 2：依複雜度估計回應大小 先把 prompt 分類，再套用倍數範圍，得到完整的回應區間： | 複雜度 | 倍數範圍 | 範例 prompt | |--------------|------------------|------------------------------------------------------| | Simple | 3× – 8× | "What is X?"、是非題、單一事實 | | Medium | 8× – 20× | "How does X work?" | | Medium-High | 10× – 25× | 附帶 context 的程式碼請求 | | Complex | 15× – 40× | 多部分的分析、比較、架構 | | Creative | 10× – 30× | 故事、文章、敘事寫作 | 回應區間 = `input_tokens × mult_min` 到 `input_tokens × mult_max`（但不要超過你模型設定的輸出 token 上限）。 ### 步驟 3：呈現深度選項 在回答**之前**呈現這個區塊，使用實際估計出來的數字： ``` Analyzing your prompt... Input: ~[N] tokens | Type: [type] | Complexity: [level] | Language: [lang] Choose your depth level: [1] Essential (25%) -> ~[tokens] Direct answer only, no preamble [2] Moderate (50%) -> ~[tokens] Answer + context + 1 example [3] Detailed (75%) -> ~[tokens] Full answer with alternatives [4] Exhaustive (100%) -> ~[tokens] Everything, no limits Which level? (1-4 or say "25% depth", "50% depth", "75% depth", "100% depth") Precision: heuristic estimate ~85-90% accuracy (±15%). ``` 各層級的 token 估計（在回應區間之內）： - 25% → `min + (max - min) × 0.25` - 50% → `min + (max - min) × 0.50` - 75% → `min + (max - min) × 0.75` - 100% → `max` ### 步驟 4：依選擇的層級回應 | 層級 | 目標長度 | 包含 | 省略 | |------------------|---------------------|-----------------------------------------------------|---------------------------------------------------| | 25% Essential | 最多 2-4 句 | 直接的答案、關鍵結論 | Context、範例、細微差異、替代方案 | | 50% Moderate | 1-3 段 | 答案 + 必要的 context + 1 個範例 | 深入分析、邊界情況、參考資料 | | 75% Detailed | 結構化的回應 | 多個範例、優缺點、替代方案 | 極端的邊界情況、窮盡的參考資料 | | 100% Exhaustive | 不設限 | 全部：完整分析、所有程式碼、所有觀點 | 沒有 | ## 捷徑：跳過提問 如果使用者已經表明層級，就直接用那個層級回應，不用問： | 他們說的話 | 層級 | |----------------------------------------------------|-------| | "1" / "25% depth" / "short version" / "brief answer" / "tldr" | 25% | | "2" / "50% depth" / "moderate depth" / "balanced answer" | 50% | | "3" / "75% depth" / "detailed answer" / "thorough answer" | 75% | | "4" / "100% depth" / "exhaustive answer" / "full deep dive" | 100% | 如果使用者在 session 稍早設定過層級，後續的回應要**默默維持它**，除非他們改變。 ## 精確度說明 這個 skill 使用啟發式估計，沒有真正的 tokenizer。準確度約 85-90%，變異 ±15%。一定要顯示免責聲明。 ## 範例 ### 會觸發 - "Give me the short version first." - "How many tokens will your answer use?" - "Respond at 50% depth." - "I want the exhaustive answer, not the summary." - "Dame la version corta y luego la detallada." ### 不會觸發 - "What is a JWT token?" - "The checkout flow uses a payment token." - "Is this normal?" - "Complete the refactor." - 使用者已經為這個 session 選好深度之後的後續問題 ## 來源 獨立的 skill，來自 [TBA — Token Budget Advisor for Claude Code](https://github.com/Xabilimon1/Token-Budget-Advisor-Claude-Code-)。 原專案還附了一個 Python 估計器 script，但這個 repo 讓這個 skill 保持自成一體，而且只用啟發式。
英文原文
--- name: token-budget-advisor description: Offer a choice of response depth (25%/50%/75%/100%) with token estimates before answering, then answer at that level. Use when the user asks to control response length or token budget, such as 'token budget', 'short version', 'brief answer', 'respuesta corta vs larga', 'cuántos tokens', 'ahorrar tokens', 'responde al 50%', 'dame la versión corta', 'quiero controlar cuánto usas'. Skip if depth is already set this session or 'token' means an auth/payment token. metadata: origin: community --- # Token Budget Advisor (TBA) Intercept the response flow to offer the user a choice about response depth **before** Claude answers. ## When to Use - User wants to control how long or detailed a response is - User mentions tokens, budget, depth, or response length - User says "short version", "tldr", "brief", "al 25%", "exhaustive", etc. - Any time the user wants to choose depth/detail level upfront **Do not trigger** when: user already set a level this session (maintain it silently), or the answer is trivially one line. ## How It Works ### Step 1 — Estimate input tokens Use the repository's canonical context-budget heuristics to estimate the prompt's token count mentally. Use the same calibration guidance as [context-budget](../context-budget/SKILL.md): - prose: `words × 1.3` - code-heavy or mixed/code blocks: `chars / 4` For mixed content, use the dominant content type and keep the estimate heuristic. ### Step 2 — Estimate response size by complexity Classify the prompt, then apply the multiplier range to get the full response window: | Complexity | Multiplier range | Example prompts | |--------------|------------------|------------------------------------------------------| | Simple | 3× – 8× | "What is X?", yes/no, single fact | | Medium | 8× – 20× | "How does X work?" | | Medium-High | 10× – 25× | Code request with context | | Complex | 15× – 40× | Multi-part analysis, comparisons, architecture | | Creative | 10× – 30× | Stories, essays, narrative writing | Response window = `input_tokens × mult_min` to `input_tokens × mult_max` (but don’t exceed your model’s configured output-token limit). ### Step 3 — Present depth options Present this block **before** answering, using the actual estimated numbers: ``` Analyzing your prompt... Input: ~[N] tokens | Type: [type] | Complexity: [level] | Language: [lang] Choose your depth level: [1] Essential (25%) -> ~[tokens] Direct answer only, no preamble [2] Moderate (50%) -> ~[tokens] Answer + context + 1 example [3] Detailed (75%) -> ~[tokens] Full answer with alternatives [4] Exhaustive (100%) -> ~[tokens] Everything, no limits Which level? (1-4 or say "25% depth", "50% depth", "75% depth", "100% depth") Precision: heuristic estimate ~85-90% accuracy (±15%). ``` Level token estimates (within the response window): - 25% → `min + (max - min) × 0.25` - 50% → `min + (max - min) × 0.50` - 75% → `min + (max - min) × 0.75` - 100% → `max` ### Step 4 — Respond at the chosen level | Level | Target length | Include | Omit | |------------------|---------------------|-----------------------------------------------------|---------------------------------------------------| | 25% Essential | 2-4 sentences max | Direct answer, key conclusion | Context, examples, nuance, alternatives | | 50% Moderate | 1-3 paragraphs | Answer + necessary context + 1 example | Deep analysis, edge cases, references | | 75% Detailed | Structured response | Multiple examples, pros/cons, alternatives | Extreme edge cases, exhaustive references | | 100% Exhaustive | No restriction | Everything — full analysis, all code, all perspectives | Nothing | ## Shortcuts — skip the question If the user already signals a level, respond at that level immediately without asking: | What they say | Level | |----------------------------------------------------|-------| | "1" / "25% depth" / "short version" / "brief answer" / "tldr" | 25% | | "2" / "50% depth" / "moderate depth" / "balanced answer" | 50% | | "3" / "75% depth" / "detailed answer" / "thorough answer" | 75% | | "4" / "100% depth" / "exhaustive answer" / "full deep dive" | 100% | If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it. ## Precision note This skill uses heuristic estimation — no real tokenizer. Accuracy ~85-90%, variance ±15%. Always show the disclaimer. ## Examples ### Triggers - "Give me the short version first." - "How many tokens will your answer use?" - "Respond at 50% depth." - "I want the exhaustive answer, not the summary." - "Dame la version corta y luego la detallada." ### Does Not Trigger - "What is a JWT token?" - "The checkout flow uses a payment token." - "Is this normal?" - "Complete the refactor." - Follow-up questions after the user already chose a depth for the session ## Source Standalone skill from [TBA — Token Budget Advisor for Claude Code](https://github.com/Xabilimon1/Token-Budget-Advisor-Claude-Code-). Original project also ships a Python estimator script, but this repository keeps the skill self-contained and heuristic-only.