Minimax Usage

Monitor Minimax Coding Plan usage to stay within API limits. Fetches current usage stats and provides status alerts.

Security Scan

The skill appears to do what it claims (check Minimax coding-plan usage) but has several inconsistencies — missing declared environment requirements, an unsafe .env sourcing path, and an undeclared dependency (jq) — that merit caution before installing or running.

Purpose & Capability

The skill's stated purpose (monitor Minimax coding-plan usage) matches what the script does (HTTP GET to minimax platform using an API key and GroupId). However the registry metadata declares no required environment variables or credentials while both SKILL.md and the script require MINIMAX_CODING_API_KEY and MINIMAX_GROUP_ID. This mismatch is incoherent and should have been declared.

Instruction Scope

SKILL.md instructs the user to create a .env 'in the same directory as the script', but the script actually sources "$(dirname "$0")/../../.env" (two directories up). That difference means the script may read a .env in an unexpected location (potentially unrelated environment data). The script only sends data to platform.minimax.io (expected), and does not appear to exfiltrate to other endpoints, but the incorrect source path is a scope creep/risk because it can pull in variables the author didn't intend.

Install Mechanism

No install spec (instruction-only plus a shell script). Nothing is downloaded or written during an install step, which is low risk. The provided script is executed locally and not installed from remote URLs.

Credentials

The script needs MINIMAX_CODING_API_KEY and MINIMAX_GROUP_ID (proportionate to the task). However the registry lists no required env vars (incoherent). Additionally the script sources a .env file from ../../.env which could load many other environment variables not intended for this skill; that's a proportionality risk. The script also relies on jq and curl but required binaries were not declared in metadata.

Persistence & Privilege

The skill does not request permanent presence (always:false). It does not modify other skills or system-wide settings and does not persist credentials; it simply reads variables and makes a single API call. Autonomous invocation is enabled by default (normal).

What to consider before installing

Before installing or running this skill: 1) Do not assume the metadata lists required credentials — the script expects MINIMAX_CODING_API_KEY and MINIMAX_GROUP_ID. 2) Inspect and fix the .env sourcing path: SKILL.md says create .env next to the script but the script sources ../../.env. Either place your .env two levels up (risky) or edit the script to source a local .env (e.g., source "$(dirname "$0")/.env"). 3) Ensure jq and curl are available (jq is used but not declared). 4) Keep the .env file minimal — only include the two Minimax values; don't put other secrets in that file if you keep it at ../../.env. 5) Run the script in an isolated environment (container or sandbox) until you confirm it behaves as expected. 6) Prefer the registry metadata to be updated to declare the env vars and required binaries; if you cannot verify or change the script, treat this skill as untrusted.

Minimax Usage Skill

Monitor Minimax Coding Plan usage to stay within limits.

Setup

Create a .env file in the same directory as the script:

MINIMAX_CODING_API_KEY=your_api_key_here
MINIMAX_GROUP_ID=your_group_id_here

Get your GroupId from: https://platform.minimax.io/user-center/basic-information (under "Basic Information")

Usage

./minimax-usage.sh

Output Example

🔍 Checking Minimax Coding Plan usage...
✅ Usage retrieved successfully:

📊 Coding Plan Status (MiniMax-M2):
   Used:      255 / 1500 prompts (17%)
   Remaining: 1245 prompts
   Resets in: 3h 17m

💚 GREEN: 17% used. Plenty of buffer.

API Details

Endpoint:

GET https://platform.minimax.io/v1/api/openplatform/coding_plan/remains?GroupId={GROUP_ID}

Required Headers:

accept: application/json, text/plain, */*
authorization: Bearer {MINIMAX_CODING_API_KEY}
referer: https://platform.minimax.io/user-center/payment/coding-plan
user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36

Limits

Metric	Value
Reset window	5 hours (dynamic)
Max target	60% usage
1 prompt ≈	15 model calls

Notes

• Coding Plan API key is exclusive to this plan (not interchangeable with standard API keys)
• Usage from 5+ hours ago is automatically released from the count