Credits Quotas Plans logo

Credits Quotas Plans

Organization
clay-run
credits-quotas-plans

Use when the user asks about credits, quotas, or plan limits, or verified usage requires a significant-spend warning or reveals a limit. Covers data-credit balance, action-execution balance, search result caps, period quotas, and upgrade paths before starting work that would only partially complete.

Overview

Publisherclay-run
Repositoryagent-plugins
Skill namecredits-quotas-plans
Stars
145
Forks
24
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by clay-run on GitHub. Read the source before you install it.

Installation

Install the Credits Quotas Plans AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/clay-run/agent-plugins/tree/main/clay/skills/credits-quotas-plans
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/clay-run/agent-plugins.git /tmp/agent-plugins
mkdir -p .claude/skills
cp -r /tmp/agent-plugins/clay/skills/credits-quotas-plans .claude/skills/credits-quotas-plans
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Credits Quotas Plans in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Credits Quotas Plans on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Credits Quotas Plans is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Credits, quotas, and plans

Follow the shared cost policy in workflows-discover-actions/cost-and-budget.md. Check headroom internally before paid work; do not announce balances or suggest purchases just because a tool returned billing data. Stop and explain a verified shortfall rather than knowingly starting a partial run. An unknown cost does not establish a shortfall or require a cost-only approval.

Triage

After checking what remains (below), route by what is short:

  • balance short — CLI top-up or billing UI (addCredits). Prefer auto top-up.
  • actionExecutionBalance short (when the field is present) — plan selector only. There is no top-up for action executions. Do not offer once, auto, or addCredits.
  • Search quota_exceeded or period cap exhausted — plan selector and/or wait for the named reset in the error message. Defer shrink/retry rules to the search skill; do not invent a top-up path for result caps.

Plan selector URL (upgrade or change plan):

bash
clay whoami | jq -r '.workspace.id'

https://app.clay.com/workspaces/<workspaceId>/billing/plan-selector

Check what remains

bash
clay credits balance | jq '{ balance, actionExecutionBalance }'

balance is the data-credit pool. actionExecutionBalance is optional — present only on action-execution pricing plans; omit or ignore it when the field is null or absent (legacy billing). Plenty of one does not cover the other.

For routine runs, clay routines get <id> includes per-item cost estimates. When the estimate applies to the configured execution and its counts are known, multiply each cost by the number of items and compare against the matching balance. See the routines skill for estimate limitations and the stop-before-partial-run rule.

Read clay credits balance --help for field semantics.

CLI top-up

Applies to data-credit balance only — not actionExecutionBalance.

Prefer auto top-up. Lead with enabling (or confirming) auto so the workspace stays funded without another interrupt. Only offer a one-time purchase if the user pushes back against auto, or if auto is unavailable.

Read clay credits top-up <subcommand> --help for the exact JSON output shape, flags, and examples; that help is the contract.

bash
clay credits top-up auto get
clay credits top-up auto enable --threshold <n> --credits <n> [--daily-spend-limit-cents <n|none>]
clay credits top-up auto disable
clay credits top-up once --credits <n> [--open]   # only if user declines auto, or auto unavailable

Auto enable limits:

  • --credits: at least 250 data credits; the plan-specific maximum is the number of credits currently equivalent to $1000
  • --daily-spend-limit-cents: optional rolling 24-hour cap, 3000–500000, or none to clear; must cover the current price of one top-up
  • --threshold: credit balance that triggers a top-up; must be at least 15% of the workspace subscription-cycle credit allowance (the server error includes the exact minimum when too low)

If the current balance is already at or below --threshold when auto is enabled, a top-up runs immediately — it does not wait for the next charge. Tell the user that enabling auto can purchase credits right away when they are already under the threshold.

Auto get/disable return the same policy shape as enable.

Once (fallback): --credits must be at least 250. Returns a checkout url; --open launches it in the browser. Credits land only after checkout completes — do not treat command exit as a topped-up balance.

Errors worth knowing (from credits balance / credits top-up):

  • auth_forbidden (exit 3) — billing-management access required
  • not_found (exit 6) — auto top-up unavailable for this workspace, or disable when not currently enabled; fall back to once or the billing UI

Do not run top-up without explicit user confirmation. credits top-up commands are gated from auto-approval in the plugin — present options and wait for the user before auto enable, once, or checkout --open.

Billing UI

Prefer CLI auto first. Use the billing UI when the user wants the browser, or as the one-time fallback after they decline auto / auto is unavailable:

bash
clay whoami | jq -r '.workspace.id'

https://app.clay.com/workspaces/<workspaceId>/home?addCredits=true

The addCredits=true query opens the buy-credits modal directly.

Search and result-cap quotas

There is no CLI to top up search result caps or period quotas. Auto top-up only replenishes credit shortfalls — it does not raise per-search or per-period result limits.

quota_exceeded (exit 1, HTTP 402) is a plan result cap or credit/usage limit — not a transient failure (do not retry with backoff). Prefer the plan selector over top-up unless the message is clearly a data-credit shortfall that top-up can fix. When the error is about results already requested vs a cap, or a named period reset, stop paging; for shrink/retry rules follow the searches skill's Quotas section — do not invent a top-up path for result caps.

Plan selector:

bash
clay whoami | jq -r '.workspace.id'

https://app.clay.com/workspaces/<workspaceId>/billing/plan-selector

Frequently asked questions

What does the Credits Quotas Plans AI skill do?

Use when the user asks about credits, quotas, or plan limits, or verified usage requires a significant-spend warning or reveals a limit. Covers data-credit balance, action-execution balance, search result caps, period quotas, and upgrade paths before starting work that would only partially complete.

Why use Credits Quotas Plans on TypingMind?

Because you install it once and use it with any model. Credits Quotas Plans is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Credits Quotas Plans in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/clay-run/agent-plugins/tree/main/clay/skills/credits-quotas-plans. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Credits Quotas Plans?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Credits Quotas Plans?

As many as you like. As long as a model supports skills, you can use Credits Quotas Plans with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Credits Quotas Plans AI skill free?

It is published on GitHub by clay-run. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇