claude-code-config: Skill for Claude Code

.claude/skills/quotas-setup/SKILL.md

quotas-setup is a skill for Claude Code from auerbachb/claude-code-config. It costs 100 tokens per session (3,432 once invoked), scanned A, original, MIT.

An account setup tool for registering multiple paid AI-service logins, such as Claude Code, Codex, or Cursor, with separate login profiles. It verifies which accounts can be reached but does not read usage totals or control spending.

In plain words
What is it for?
Use it to add another subscription account, reconnect an expired login, or see which registered accounts are available. Login is completed through the provider's own interactive sign-in flow.
Why use it?
It keeps different subscriptions separated and avoids passing passwords, tokens, or cookies through the tool. It also makes clear that quota and spending decisions belong to the provider's own account interface.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; positional $N argument.

This is auerbachb/claude-code-config's own configuration. It tells Claude Code how to work on claude-code-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/skills/quotas-setup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for quotas-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/auerbachb/claude-code-config/quotas-setup/github.svg)](https://agentmods.dev/skills/auerbachb/claude-code-config/quotas-setup)
Your own site
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/quotas-setup"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/quotas-setup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for quotas-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/quotas-setup"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/quotas-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00100 $0.03432
Opus 5 $0.00050 $0.01716
Sonnet 5 $0.00020 $0.00686
Haiku 4.5 $0.00010 $0.00343

Measured today against content hash 297b0adb88db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

quotas-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/quotas-setup/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Register the accounts behind the owner's parallel AI subscriptions, give each one an isolated login profile, and report which are reachable.

Display and configuration only. Nothing this skill produces may gate dispatch, pause work, downgrade a model, or feed credit-budget.sh. Quota and spend authority belongs to Anthropic's own in-app UI and upstream harness signals — see .claude/rules/safety.md §"Anthropic Quota & Spend Authority". Reading usage figures is a different tool (/quotas, increment 2); this skill stops at a validated account list.

No credential ever passes through you. Every login is the provider's own interactive flow (magic link, SSO, CAPTCHA) — and for Cursor it is not even this tool's to run: the Cursor IDE holds that login. The helper launches what it can and waits — it never types, reads, prints, or stores a password, token, or cookie, and neither do you. If a login needs the user's hands, say so and stop; do not offer to type credentials.

Step 1 — Resolve the helper

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}
AI_QUOTAS_SETUP_SH=$(resolve_script ai-quotas-setup.sh || true)
[[ -n "$AI_QUOTAS_SETUP_SH" ]] || { echo "ERROR: ai-quotas-setup.sh not found (checked all three paths) — account registration unavailable" >&2; exit 1; }

STOP if the helper does not resolve: print that one line and end. Do not hand-roll the registry — a second writer to ~/.claude/ai-quotas.json is how the config and the profile directories drift apart.

Step 2 — Route the request

The user asked Run
nothing, "list", "which accounts" "$AI_QUOTAS_SETUP_SH" list
"add <provider> <label>" "$AI_QUOTAS_SETUP_SH" add <provider> <label>
"register it now, I'll log in later" "$AI_QUOTAS_SETUP_SH" add <provider> <label> --no-login
"call it <name>", "nickname this account" "$AI_QUOTAS_SETUP_SH" nick <label> "<name>" [<provider>]
"remove <label>" "$AI_QUOTAS_SETUP_SH" remove <label> [<provider>]
"re-login <label>", an account showing needs-login "$AI_QUOTAS_SETUP_SH" relogin <label> [<provider>]
"take a reading every day", "install the snapshot job" "$AI_QUOTAS_SETUP_SH" schedule install
"is the daily job running" "$AI_QUOTAS_SETUP_SH" schedule status
"stop the daily job" "$AI_QUOTAS_SETUP_SH" schedule remove

Read the full file on GitHub · 230 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +4 lines · +6 tokens per session 297b0adb88db
  2. yesterday Changed · +59 lines · +6 tokens per session e76627f5811f
  3. 2d ago Changed · +13 lines · +20 tokens per session 8586bd6fef83
  4. 4d ago First seen · 154 lines · 68 tokens per session scan A 046c8ad43ca0

Subscribe to this mod's changes

quotas-setup is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 3,432 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.

Related

Other skills, from other repositories

community-research-insight

Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

clawdotnet/openclaw.net · 41 tokens

docs

Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…

The01Geek/prflow · 97 tokens

install-jazz-github-action

Set up Jazz as a GitHub Action for automated PR code review and on-demand /jazz PR assistance. Use when the user asks to add Jazz to CI, create a GitHub Action workflow, set up PR review automation, enable /jazz commands on PRs, or integrate Jazz with GitHub.

lvndry/jazz · 69 tokens

analysis-provenance

Identify code ownership before modifying validators or linters. Checks file headers for provenance indicators, reviews documentation, and determines provenance as UPSTREAM, LOCAL, VENDOR, or UNKNOWN. Prevents accidental modification of upstream tools.

rjmurillo/ai-agents · 48 tokens

pir-action-tracker

Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…

Perseus-Computing-LLC/perseus · 78 tokens

robin

Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…

antongulin/robin · 92 tokens