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 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/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/eldanring/qubicl/plan"><img src="https://agentmods.dev/badge/skills/eldanring/qubicl/plan.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 | $0.00040 | $0.00238 |
| Opus 5.5 | $0.00016 | $0.00095 |
| Sonnet 5.5 | $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 1mo 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.
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.
- 1mo ago Changed 5660d8fcd56b
- 1mo ago First seen · 22 lines · 40 tokens per session scan A f740ea5d9fdc
plan is a skill published in the GitHub repository EldanRing/qubicl (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 238 once invoked, about $0.0002 per session on Opus 5.5. 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
browser-bridge
Token-efficient Chrome tab inspection, interaction, and patching via local bridge extension (CLI: bbx). Reads live DOM, styles, console, network, and storage from a real Chrome tab with lower token cost than screenshots.
douyin-skills
A local automation toolkit for Douyin, the Chinese short-video platform, and its creator center. It uses the computer’s Chrome browser to handle account access, content search, publishing, and basic interactions.
douyin-env
An environment setup and troubleshooting guide for the Douyin automation toolkit. It checks the computer’s Python, Node.js, browser, dependencies, graphics support, and local browser profile.
douyin-publish
A browser workflow for preparing and publishing image posts or videos on Douyin, a Chinese short-video social platform. It uploads local media, fills the post details, checks the page, and publishes only after confirmation.
douyin-auth
A command-line tool for signing in to Douyin, a Chinese short-video platform, and managing named accounts. It supports QR-code and phone-code login through a browser.
douyin-interact
An automation tool for interacting with specified public Douyin videos or notes, including checking or changing likes and favourites and adding comments.