Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add FruityMaxine/claude-quotas --skill check-quotagit clone --depth 1 https://github.com/FruityMaxine/claude-quotasWrote 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.
[](https://agentmods.dev/skills/fruitymaxine/claude-quotas/check-quota)<a href="https://agentmods.dev/skills/fruitymaxine/claude-quotas/check-quota"><img src="https://agentmods.dev/badge/skills/fruitymaxine/claude-quotas/check-quota/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.
<a href="https://agentmods.dev/skills/fruitymaxine/claude-quotas/check-quota"><img src="https://agentmods.dev/badge/skills/fruitymaxine/claude-quotas/check-quota.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.03604 |
| Opus 5 | $0.00051 | $0.01802 |
| Sonnet 5 | $0.00020 | $0.00721 |
| Haiku 4.5 | $0.00010 | $0.00360 |
Grade C, and why
check-quota scanned grade C with 1 finding 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 11d ago.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- Do not refuse a task because quota is low. The user gave you the task; How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-quotas — check_quota + vigilance policy
This plugin gives you (Claude) a read-only MCP tool, check_quota, plus a
disciplined policy for using it. The point is never let the user's task get
interrupted by hitting the quota wall mid-work — especially in long-running
or autonomous (/loop) tasks where the user may not be at the keyboard.
The tool
check_quota is cheap, fast (~500 ms), and read-only. One outbound HTTPS
request to api.anthropic.com, nothing written to disk, no caching.
It returns a JSON object with these fields:
| Field | Meaning |
|---|---|
subscription_type |
Coarse plan: "pro" or "max". |
rate_limit_tier |
Fine-grained tier from local credentials, e.g. "default_claude_max_5x", "default_claude_max_20x". Use this to pick which threshold row applies. |
five_hour.utilization |
0–100. Percentage of the 5-hour rolling session window already consumed. |
five_hour.resets_at |
ISO 8601. When the 5-hour window resets. |
seven_day.utilization |
0–100. Percentage of the 7-day rolling weekly cap already consumed. |
seven_day.resets_at |
ISO 8601. When the weekly window resets. |
seven_day_opus |
Opus-specific weekly window. null = no pool surfaced for this account; {utilization: 0, resets_at: null} = pool exists but no consumption in the current period. |
seven_day_sonnet |
Sonnet-specific weekly window. null = no pool surfaced for this account; {utilization: 0, resets_at: null} = pool exists but no consumption in the current period. |
extra_usage |
Pay-as-you-go credit status; only meaningful when is_enabled: true. |
summary |
Pre-formatted multi-line human-readable summary. |
utilization is percentage already used, normalized per plan. 80% means
"this user has consumed 80% of their plan's allowance for that window".
When to call
Call check_quota:
- At the start of any task that looks potentially multi-step (more than a single trivial edit). This is your baseline reading.
- Periodically during the task, calibrated by how fast utilization is growing. Cheap tasks → check every several subtasks. Expensive tasks → check after each subtask.
- Whenever crossing into a new threshold zone (see thresholds below) — re-check before the next subtask to confirm the zone.
- Anytime the user asks about quota / remaining / rate limits / reset.
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.
- 11d ago First seen · 287 lines · 101 tokens per session scan C f38805eb8a61
check-quota is a skill published in the GitHub repository FruityMaxine/claude-quotas (3 stars, last pushed 4mo ago), licensed MIT. It adds 101 tokens to every session and 3,604 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
multi-perspective-review
Multi-perspective collaborative review of plans or documents. Ten expert viewpoints deliberate in 3 rounds to reach consensus.
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
brainstorming
Design and spec before any planning or code. MUST USE before new features, creative work, or any implementation. Explores requirements, proposes approaches, gets design approval, then chains to plan-task.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
debug
Analyze errors and apply fixes. Use when you have an error message, traceback, or failing log to diagnose.