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:
- 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.
Original project also ships a Python estimator script, but this repository keeps the skill self-contained and heuristic-only.
Source: affaan-m/ECC → skills/token-budget-advisor/SKILL.md
Also appears in: hashgraph-online/awesome-codex-plugins/plugins/Colin4k1024/tsp/skills/token-budget-advisor/SKILL.md
1---
2name: token-budget-advisor-3
3description: ">- Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: \"token budget\", \"token count\", \"token usage\", \"token limit\", \"response length\", \"answer depth\", \"short version\", \"brief answer\", \"detailed answer\", \"exhaustive answer\", \"respuesta corta vs larga\", \"cuántos tokens\", \"ahorrar tokens\", \"responde al 50%\", \"dame la versión corta\", \"quiero controlar cuánto usas\", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or \"token\" refers to auth/session/payment tokens rather than response size."
4category: business-and-finance
5source_repo: affaan-m/ECC
6source_path: "skills/token-budget-advisor/SKILL.md"
7source_url: https://github.com/affaan-m/ECC/blob/HEAD/skills/token-budget-advisor/SKILL.md
8metadata:
9 source: https://skillmd.com/skills/affaan-m/token-budget-advisor-3
10---
11
12# Token Budget Advisor (TBA)
13
14Intercept the response flow to offer the user a choice about response depth **before** Claude answers.
15
16## When to Use
17
18- User wants to control how long or detailed a response is
19- User mentions tokens, budget, depth, or response length
20- User says "short version", "tldr", "brief", "al 25%", "exhaustive", etc.
21- Any time the user wants to choose depth/detail level upfront
22
23**Do not trigger** when: user already set a level this session (maintain it silently), or the answer is trivially one line.
24
25## How It Works
26
27### Step 1 — Estimate input tokens
28
29Use the repository's canonical context-budget heuristics to estimate the prompt's token count mentally.
30
31Use the same calibration guidance as [context-budget](../context-budget/SKILL.md):
32
33- prose: `words × 1.3`
34- code-heavy or mixed/code blocks: `chars / 4`
35
36For mixed content, use the dominant content type and keep the estimate heuristic.
37
38### Step 2 — Estimate response size by complexity
39
40Classify the prompt, then apply the multiplier range to get the full response window:
41
42| Complexity | Multiplier range | Example prompts |
43|--------------|------------------|------------------------------------------------------|
44| Simple | 3× – 8× | "What is X?", yes/no, single fact |
45| Medium | 8× – 20× | "How does X work?" |
46| Medium-High | 10× – 25× | Code request with context |
47| Complex | 15× – 40× | Multi-part analysis, comparisons, architecture |
48| Creative | 10× – 30× | Stories, essays, narrative writing |
49
50Response window = `input_tokens × mult_min` to `input_tokens × mult_max` (but don’t exceed your model’s configured output-token limit).
51
52### Step 3 — Present depth options
53
54Present this block **before** answering, using the actual estimated numbers:
55
56```
57Analyzing your prompt...
58
59Input: ~[N] tokens | Type: [type] | Complexity: [level] | Language: [lang]
60
61Choose your depth level:
62
63[1] Essential (25%) -> ~[tokens] Direct answer only, no preamble
64[2] Moderate (50%) -> ~[tokens] Answer + context + 1 example
65[3] Detailed (75%) -> ~[tokens] Full answer with alternatives
66[4] Exhaustive (100%) -> ~[tokens] Everything, no limits
67
68Which level? (1-4 or say "25% depth", "50% depth", "75% depth", "100% depth")
69
70Precision: heuristic estimate ~85-90% accuracy (±15%).
71```
72
73Level token estimates (within the response window):
74- 25% → `min + (max - min) × 0.25`
75- 50% → `min + (max - min) × 0.50`
76- 75% → `min + (max - min) × 0.75`
77- 100% → `max`
78
79### Step 4 — Respond at the chosen level
80
81| Level | Target length | Include | Omit |
82|------------------|---------------------|-----------------------------------------------------|---------------------------------------------------|
83| 25% Essential | 2-4 sentences max | Direct answer, key conclusion | Context, examples, nuance, alternatives |
84| 50% Moderate | 1-3 paragraphs | Answer + necessary context + 1 example | Deep analysis, edge cases, references |
85| 75% Detailed | Structured response | Multiple examples, pros/cons, alternatives | Extreme edge cases, exhaustive references |
86| 100% Exhaustive | No restriction | Everything — full analysis, all code, all perspectives | Nothing |
87
88## Shortcuts — skip the question
89
90If the user already signals a level, respond at that level immediately without asking:
91
92| What they say | Level |
93|----------------------------------------------------|-------|
94| "1" / "25% depth" / "short version" / "brief answer" / "tldr" | 25% |
95| "2" / "50% depth" / "moderate depth" / "balanced answer" | 50% |
96| "3" / "75% depth" / "detailed answer" / "thorough answer" | 75% |
97| "4" / "100% depth" / "exhaustive answer" / "full deep dive" | 100% |
98
99If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.
100
101## Precision note
102
103This skill uses heuristic estimation — no real tokenizer. Accuracy ~85-90%, variance ±15%. Always show the disclaimer.
104
105## Examples
106
107### Triggers
108
109- "Give me the short version first."
110- "How many tokens will your answer use?"
111- "Respond at 50% depth."
112- "I want the exhaustive answer, not the summary."
113- "Dame la version corta y luego la detallada."
114
115### Does Not Trigger
116
117- "What is a JWT token?"
118- "The checkout flow uses a payment token."
119- "Is this normal?"
120- "Complete the refactor."
121- Follow-up questions after the user already chose a depth for the session
122
123## Source
124
125Standalone skill from [TBA — Token Budget Advisor for Claude Code](https://github.com/Xabilimon1/Token-Budget-Advisor-Claude-Code-).
126Original project also ships a Python estimator script, but this repository keeps the skill self-contained and heuristic-only.
127
128---
129
130**Source:** [`affaan-m/ECC`](https://github.com/affaan-m/ECC) → `skills/token-budget-advisor/SKILL.md`
131
132**Also appears in:** `hashgraph-online/awesome-codex-plugins/plugins/Colin4k1024/tsp/skills/token-budget-advisor/SKILL.md`