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 humanerd-drew/opencode-drewgent --skill token-plan-checkgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/token-plan-check)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/token-plan-check"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/token-plan-check.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.07577 |
| Opus 5 | $0.00000 | $0.03789 |
| Sonnet 5 | $0.00000 | $0.01515 |
| Haiku 4.5 | $0.00000 | $0.00758 |
Grade C, and why
token-plan-check scanned grade C with 2 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf acp_adapter/__pycache__` 필수 (stale .pyc가 rename 무시) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "https://api.minimax.io/v1/api/openplatform/coding_plan/remains" \ How it starts
The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: token-plan-check description: "MiniMax Token Plan 사용량/리셋을 터미널에서 즉시 확인하거나, zsh RPROMPT statusline으로 영구 통합하는 절차. 사용자가 토큰 얼마나 남았는지, 리셋까지 얼마인지, 주간 한도 현황을 물을 때 사용. API endpoint: GET https://api.minimax.io/v1/api/openplatform/coding_plan/remains. 기존 script 위치: ~/.{{AGENT_NAME_LOWER}}/scripts/minimax_usage.py. Statusline 파일: ~/.{{AGENT_NAME_LOWER}}/.zshrc_aliases." title: Token Plan Check — Terminal Usage & Statusline domain: brain space: growth type: workflow tags: [token-plan, minimax, statusline, rprompt, zsh, terminal, {{AGENT_NAME_LOWER}}] created: 2026-06-02 updated: 2026-06-02 links:
- "[[@memory/growth/INTEGRATION_PROTOCOL]]"
- "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁secrets_in_code.neuron]]"
- "[[@identity/brain/{{AGENT_NAME}}-brain/P0-brainstem/禁/禁filesystem_truth.neuron]]"
- "[[@identity/brain/rules]]"---
Token Plan Check — Terminal Usage & Statusline Integration
MiniMax Token Plan (coding_plan) 사용량을 터미널/RPROMPT에서 확인하는 표준 절차.
트리거 조건
다음 중 하나라도 해당되면 이 스킬을 로드:
- "내 토큰 사용량 좀 보여줘" 류 task
- "리셋까지 남은 시간" 류 task
- "주간 한도 / 이번 주 사용량" 류 task
- "Token Plan statusline / RPROMPT 영구 표시" 류 통합 task
- "platform.minimax.io/console 안 가고 보고 싶어" 류 자동화 task
1단계: 기존 자산 확인
이미 구현된 것 (2026-06-02 작업):
| 자산 | 경로 | 용도 |
|---|---|---|
| 메인 스크립트 | ~/.{{AGENT_NAME_LOWER}}/scripts/minimax_usage.py |
한 번 조회 / watch / json / cache write / RPROMPT |
| zsh 통합 파일 | ~/.{{AGENT_NAME_LOWER}}/.zshrc_aliases |
aliases + RPROMPT 함수 |
| 캐시 | ~/.{{AGENT_NAME_LOWER}}/cache/minimax_usage.json |
API 응답 (60s TTL) |
| 잠금 | ~/.{{AGENT_NAME_LOWER}}/cache/minimax_usage.json.lock |
bg refresh 중복 spawn 방지 (PID) |
메인 스크립트 모드:
minimax_usage.py # 컬러 pretty 출력
minimax_usage.py --json # raw API JSON
minimax_usage.py --watch 30 # 30초마다 refresh, Ctrl-C로 종료
minimax_usage.py --write-cache P # fetch + atomic write, silent
minimax_usage.py --rprompt # RPROMPT 한 줄 문자열 (cache-first)
minimax_usage.py --maybe-refresh # cache stale일 때만 bg refresh spawn
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.
- 4d ago First seen · 436 lines · 0 tokens per session scan C ef54b9f7d691
token-plan-check is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,577 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.