Claude MarketplacesSubmit
affaan-m avatar

Token Budget Advisor

affaan-m/ecc

Intercepts Claude's response flow to let you pick how deep an answer you want before it starts writing. Triggers when you mention token budget, response length, or ask for a "short version" versus "exhaustive answer." Uses heuristic token estimation (no real tokenizer, roughly 85-90% accurate) to show you four depth levels with projected token counts, then responds accordingly. The 25% level gives you 2-4 sentences max, 100% holds nothing back. Honestly useful if you're token-conscious or just want control over verbosity without rephrasing your question. Maintains your choice across follow-ups in the same session. Supports Spanish variants too.

skills.sh installs
5.7K
GitHub stars
300.3K
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill token-budget-advisor --agent claude-code

Installs into .claude/skills of the current project.

Files

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:

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/affaan-m/ecc
Categories
Backend & APIs, Release Management, Office & Documents, Finance & Trading
First seen
Jul 14, 2026

More from affaan-m/ecc

All 263

Recommended

More Backend & APIs
1wondelai avatarddia-systemswondelai/skillsDesign data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choi5.7Kskills.sh installs
2mvanhorn avatarprinting-press-amendmvanhorn/cli-printing-pressAmend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled 5.7Kskills.sh installs
3affaan-m avatarmotion-advancedaffaan-m/eccAdvanced motion patterns for React / Next.js — drag & drop, gestures, text animations, SVG path drawing, custom hooks, imperative sequences (useAnimate), loader5.6Kskills.sh installs
4affaan-m avatarcost-aware-llm-pipelineaffaan-m/eccCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.5.6Kskills.sh installs
5mongodb avatarmongodb-connectionmongodb/agent-skillsOptimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing o5.6Kskills.sh installs
6jeffallan avatarplaywright-expertjeffallan/claude-skillsUse when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke to write test scripts, create page objects,5.6Kskills.sh installs