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 agentmods add skills/eldanring/qubicl/plannpx skills add EldanRing/qubicl --skill plangit clone --depth 1 https://github.com/EldanRing/qubiclWrote 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/eldanring/qubicl/plan)<a href="https://agentmods.dev/skills/eldanring/qubicl/plan"><img src="https://agentmods.dev/badge/skills/eldanring/qubicl/plan.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 | $0.00040 | $0.00238 |
| Opus 5 | $0.00020 | $0.00119 |
| Sonnet 5 | $0.00008 | $0.00048 |
| Haiku 4.5 | $0.00004 | $0.00024 |
Grade A, and why
plan 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.
What it actually says
Plan
Plan the requested work without implementing it. Inspect relevant context with read-only Qubicl tools. Do not change implementation files, start deployments, publish, or commit as part of planning.
Return a concise Markdown plan in the conversation. If the user requests a saved plan, writing that plan is the only planned file change: prefer write_file for a new plan and edit_file for an existing one. Use a user-provided destination; otherwise use .agents/plans/ with a descriptive kebab-case filename. A request for read-only planning does not authorize creating a plan file.
Include only useful sections:
- goal and success criteria;
- current evidence and assumptions;
- ordered implementation steps;
- files or components likely to change;
- validation and rollback;
- risks, tradeoffs, and unresolved decisions.
Use exact local paths and commands when known. Clearly label anything inferred. End by summarizing the decisions required before implementation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed 5660d8fcd56b
- 5d ago First seen · 22 lines · 40 tokens per session scan A f740ea5d9fdc
plan is a skill published in the GitHub repository EldanRing/qubicl (4 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 238 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
project-release
Prepare, publish, verify, or recover a cloakbrowser-mcp release only when the user explicitly requests release work. Require a Prompt MCP-confirmed target version and stability, follow the repository's version, changelog, PR, GitHub Release, npm, Docker, MCP Registry, and docs process, and never tag, publish…
douyin-skills
抖音网页版与创作者中心的本地自动化技能包入口。用于组合登录、搜索、热门话题、图文/视频发布、点赞、收藏、评论、分享链接，或解释整体能力、安全边界与多步骤流程；单一任务优先使用对应的 douyin- 子技能。.
douyin-publish
在抖音创作者中心填写并发布图文或视频作品，包括本地素材上传、视频封面设置、音乐选择、发布前校验和显式确认点击。用户要求发布抖音图文/视频或检查待发布内容时使用；不用于草稿管理或定时发布。.
douyin-auth
只使用 python "{baseDir}/../../scripts/cli.py" 。如果系统只有 python3，替换命令名。不要使用其他抖音登录工具。.
douyin-interact
对明确指定的抖音公开 video 或 note 作品执行一次点赞、收藏或评论，或返回分享链接。用户要求点赞、收藏、评论、取消相应状态或获取抖音作品链接时使用。.
douyin-env
检查、安装、迁移和排查 douyin-skills 本地运行环境，包括 Python、Node.js、ws、Chrome/Chromium、图形环境和本地 Profile。用户要求安装、配置、部署、迁移、环境自检或解决依赖问题时使用。.