New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Quota Interpretation Rules

by kunchenguid in kunchenguid/quota-axi

Specifies how quota-axi reads LLM subscription quota windows, derives pace and runway, computes a selection signal and renders output in TOON, JSON and TUI tiers.

MITAuto-check passedAI & LLM Engineering

Install Quota Interpretation Rules

skills CLI
$ npx skills add kunchenguid/quota-axi --skill quota-interpretation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kunchenguid/quota-axi quota-interpretation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kunchenguid/quota-axi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/quota-interpretation .claude/skills/quota-interpretation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
quota-interpretation
GitHub stars
146
Token cost
~1.2k tokens
SKILL.md length
570 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Specifies how quota-axi reads LLM subscription quota windows, derives pace and runway, computes a selection signal and renders output in TOON, JSON and TUI tiers.

  • Works in 4 steps: Default TOON Report (src/render.ts) → JSON Tier Splitting (--json vs --full) → Human Terminal Interface (--tui) → …
  • Changing how quota-axi computes pace, runway or availability
  • SKILL.md covers Quota Availability & Bound…, Pace & Runway Calculations and Output Formats & Tier Splitting
  • Needs SELECTION_SCALAR_KEY

What it does

This is a specification for how quota-axi, a tool that shows agents the quota windows on LLM subscriptions, interprets provider data. It covers effective availability across scopes such as all models, product scopes and model scopes, plus a bound-conflict rule: when every window metered for a scope shows allowance but an inherited account-wide window shows zero, the scope is reported as unknown instead of exhausted.

Pace and runway rules assume cycle-average consumption over the active window. The reserve in percentage points is positive when usage lags the elapsed time and negative when it runs ahead of the reset clock. Runway combines all binding bounds and is never cached, and the selection signal is computed only from reported figures and withheld when a bounding window lacks usable pace data. quota-axi publishes data only and never routes, recommends or ranks. Output rendering tiers are covered as well.

When your agent uses it

  • Changing how quota-axi computes pace, runway or availability
  • Understanding why a quota scope shows unknown instead of exhausted
  • Checking the rules behind the selection signal before building on it

Example prompts

  • “Explain how quota-axi calculates reserve percentage points for a usage window.”
  • “Why does a model scope report unknown when the account-wide window shows zero.”
  • “Update the pace calculation in src/pace.ts without breaking the documented rules.”

Requirements

  • The quota-axi repository or its source files

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Default TOON Report (src/render.ts)
  2. JSON Tier Splitting (--json vs --full)
  3. Human Terminal Interface (--tui)
  4. CLI Fast Path

What it can do on your machine

Read from SKILL.md and the folder at commit 8ba593c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • SELECTION_SCALAR_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Quota Interpretation Rules loads about 1.2k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 570 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kunchenguid/quota-axi at commit 8ba593c, republished under its MIT licence (© kunchenguid). 570 words, ~1,237 tokens.

Download SKILL.mdSave it as .claude/skills/quota-interpretation/SKILL.md (or your agent's skills folder).
name
quota-interpretation
description
Rules and algorithms for quota interpretation, pace calculation, runway derivation, selection signals, and output tier rendering (TOON, JSON, TUI) in quota-axi.
user-invocable
false

Quota Interpretation, Pace & Output Models

This document specifies the mathematics and presentation rules for quota interpretation, runway derivation, pace calculations, and output format tiering in quota-axi.

Quota Availability & Bound Conflicts

Implemented in src/interpretation.ts:

  • Effective Availability: Analyzes provider windows across all scopes (all_models, product scopes, model scopes).
  • Bound Conflict Detection:
    • availability() accepts an optional own-windows argument.
    • When every window metered strictly for a scope reports remaining allowance, but an inherited account-wide window reports zero, quota-axi publishes effectiveAvailability[].boundConflict and reports the scope status as unknown rather than asserting exhausted_now or effective 0.
    • Used for Codex model windows (additional_rate_limits/rateLimitsByLimitId). Other providers keep their account bounds unless empirical proof of non-enforcement exists.

Pace & Runway Calculations

Implemented in src/pace.ts:

  • Cycle-Average Pace: Every projection assumes cycle-average consumption across the active window. There is no projectionBasis field anywhere in the API model.
  • Reserve Percentage Points (reservePercentPoints):
    • Quantifies how usage tracks against elapsed window time.
    • Positive values indicate usage is tracking behind the elapsed time clock (headroom remaining).
    • Negative values indicate usage is running ahead of the reset clock (burn rate higher than cycle average).
  • Effective Usable Runway: Aggregates all authoritative bounds to determine time until exhaustion, preserving uncertainty if any binding window lacks timing metadata. Runway is dynamic and never cached.
  • Selection Signal (effectiveAvailability[].selection):
    • Computed purely from reported figures via summarizeEffectiveSelection in src/pace.ts.
    • Published field name is centralized in SELECTION_SCALAR_KEY in src/types.ts.
    • If any bounding window lacks usable pace data, the whole scope is deemed unmeasurable (no scalar published, unmeasurableWindowIds listed). A not-yet-triggered zero-use window (no resetsAt plus zero usage) is fully available and is excluded from the weighted mean instead of blocking; when every bounding window is untriggered the scope publishes no scalar and reports unknown with no unmeasurableWindowIds.
    • Data only: quota-axi never routes, recommends, or ranks winners.

Output Formats & Tier Splitting

Show full SKILL.md (274 more words)Show less
1. Default TOON Report (src/render.ts)

Structured into three concise decision blocks:

  1. quota[]: One fully populated row per measurable scope.
  2. exhaustion[]: Sparse block for finite-runway scopes, joined on provider + scope.
  3. attention[]: Sparse block capturing every non-nominal condition (degraded sources, warnings, unmeasurable scopes, soft expiry).

Core Invariants:

  • Every requested provider must appear in quota[] or attention[], except providers with positive evidence of absence, which default TOON omits and counts in a single help line; --full and an explicit --provider name them.
  • quota[] rows preserve provider declaration order and are never metric-sorted.
  • spendPriority renders literal unknown, never 0. An unknown or stale scope receives no quota[] row; any finite runway is preserved in attention[].
2. JSON Tier Splitting (--json vs --full)
  • --json: Normalized quota model with derivation inputs demoted to --full.
  • --full: Includes account identities, diagnostic logs, and per-source attempts.
  • Demotion Rule: Demote at renderer serialization time only (quotaJsonReport in src/render.ts). The in-memory model retains all fields so --tui and --full have full context.
3. Human Terminal Interface (--tui)
  • Pure card renderer in src/tui.ts; interactive live loop in src/tui-live.ts.
  • Viewport Management: renderQuotaTui is height-independent. src/tui-viewport.ts (scrollFrame) windows the output to fit terminal dimensions, clipping oversized lines and providing scroll affordances without terminal overflow.
  • Humanized Presentation:
    • through_reset renders as on pace ✓.
    • Pace is visualized via bar fill and ┃ marker (no multiple chip or legend).
    • Projected exhaustion displays as relative countdown (empty in Nd Nh).
    • Headline bar uses the binding window's own label (week, session, credits).
4. CLI Fast Path
  • Bare -v, -V, or --version routes through axi-sdk-js/fast-path and the leaf src/version.ts.
  • Dynamically imports src/cli.js so provider dependencies and network graph never load on version checks.

© kunchenguid, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/quota-interpretation of kunchenguid/quota-axi.

Open the folder on GitHubat commit 8ba593c

Compare with similar skills

Quota Interpretation Rules next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Quota Interpretation Rules compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Quota Interpretation Rules this skillkunchenguid/quota-axi146—~1.2kAutomated safety check: PassMIT
LLM Gatewaysickn33/agentic-awesome-skills47k1 repos~2.1kAutomated safety check: PassMIT
Token OptimizerLeoYeAI/openclaw-master-skills2.2k—~4.2kAutomated safety check: PassMIT
Token OptimizerLeoYeAI/openclaw-master-skills2.2k—~5.2kAutomated safety check: PassMIT
Pp Groqmvanhorn/printing-press-library2.1k—~7.9kAutomated safety check: NotesApache-2.0
Antigravityyuting0624/antigravity-for-claude-code377—~9.1kAutomated safety check: PassMIT

Similar skills

  • LLM Gateway

    sickn33/agentic-awesome-skills

    Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.

    47k GitHub starsUsed in 1 repo~2.1k tokens
    Backend & APIsAuto-check passed

  • Token Optimizer

    LeoYeAI/openclaw-master-skills

    Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and multi-provider fallbacks.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Token Optimizer

    LeoYeAI/openclaw-master-skills

    Reduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL…

    2.2k GitHub stars~5.2k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Pp Groq

    mvanhorn/printing-press-library

    Every Groq endpoint in your terminal, plus a local ledger that tracks token cost and rate-limit budget.

    2.1k GitHub stars~7.9k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Antigravity

    yuting0624/antigravity-for-claude-code

    Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.

    377 GitHub stars~9.1k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Honey

    Green-PT/honey-for-devs

    Write less code and say less about it. An agent skill from Green-PT/honey-for-devs.

    313 GitHub stars~3.5k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from kunchenguid/quota-axi

  • quota-axi Release and CI Rules

    kunchenguid/quota-axi

    Documents release automation, CI workflow constraints, the contribution gate and generated-file rules for the quota-axi repository, driven by release-please.

    146 GitHub stars~934 tokensUpdated today
    Auto-check passed

  • Quota Cache Architecture

    kunchenguid/quota-axi

    Documents how quota-axi keeps its disk cache: location, strict file permissions, no stored secrets, and context-scoped identifiers that stop snapshots crossing accounts.

    146 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Quota Provider Adapter Notes

    kunchenguid/quota-axi

    Reference of credential sources, quota windows, endpoint shapes, error recovery and quirks for each provider supported by the quota-axi tool.

    146 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Quota Provider Onboarding

    kunchenguid/quota-axi

    Sets the rules and checklist for adding a new quota provider, or changing an existing adapter, in quota-axi, covering credential sources, liveness probes and tests.

    146 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Quota Axi

    kunchenguid/quota-axi

    Report local Claude, Codex, Cursor, GitHub Copilot, Grok, Kimi, Z.AI, Alibaba, OpenCode Go, Antigravity, Command Code, MiniMax, MiMo, DeepSeek, OpenRouter, ElevenLabs, Devin, Muse, and Higgsfield…

    146 GitHub stars~547 tokensUpdated today
    Auto-check passed

Categories

Questions about Quota Interpretation Rules

What does Quota Interpretation Rules do?

Specifies how quota-axi reads LLM subscription quota windows, derives pace and runway, computes a selection signal and renders output in TOON, JSON and TUI tiers. This is a specification for how quota-axi, a tool that shows agents the quota windows on LLM subscriptions, interprets provider data. It covers effective availability across scopes such as all models, product scopes and model scopes, plus a bound-conflict rule: when every window metered for a scope shows allowance but an inherited account-wide window shows zero, the scope is reported as unknown instead of exhausted.

When should I use Quota Interpretation Rules?

Quota Interpretation Rules fits situations like: changing how quota-axi computes pace, runway or availability; understanding why a quota scope shows unknown instead of exhausted; checking the rules behind the selection signal before building on it.

How do I install Quota Interpretation Rules in Claude Code?

Run `npx skills add kunchenguid/quota-axi --skill quota-interpretation -a claude-code`. Or copy the skill folder (skills/quota-interpretation in kunchenguid/quota-axi) into .claude/skills/quota-interpretation in your project. Claude Code loads it when a task matches its description.

How do I install Quota Interpretation Rules in Codex?

Run `npx skills add kunchenguid/quota-axi --skill quota-interpretation -a codex`. Or copy the skill folder (skills/quota-interpretation in kunchenguid/quota-axi) into .agents/skills/quota-interpretation in your project. Codex loads it when a task matches its description.

Can I use Quota Interpretation Rules in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kunchenguid/quota-axi --skill quota-interpretation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quota-interpretation, .gemini/skills/quota-interpretation, .github/skills/quota-interpretation and .opencode/skills/quota-interpretation in your project.

What does Quota Interpretation Rules need to run?

Going by SKILL.md and its folder, Quota Interpretation Rules needs credentials named SELECTION_SCALAR_KEY. Our summary lists: The quota-axi repository or its source files.

Does Quota Interpretation Rules access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Quota Interpretation Rules safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Quota Interpretation Rules use?

Quota Interpretation Rules is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Quota Interpretation Rules use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Quota Interpretation Rules?

Skills that share tags, products or a category with Quota Interpretation Rules: LLM Gateway (sickn33/agentic-awesome-skills, 47k stars), Token Optimizer (LeoYeAI/openclaw-master-skills, 2.2k stars), Token Optimizer (LeoYeAI/openclaw-master-skills, 2.2k stars) and Pp Groq (mvanhorn/printing-press-library, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Quota Interpretation Rules?

kunchenguid (a GitHub user) maintains it in kunchenguid/quota-axi, which has 146 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 9, 2026.

Source: kunchenguid/quota-axi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.