cubox-research

A research skill for searching a personal Cubox collection, where Cubox is a service for saving articles and web pages. It searches by topic or question, tries multiple keywords and search modes, and fetches details from the best matches.

In plain words
What is it for?
Use it to find saved articles, archived pages, or collected research in Cubox. It can return article details, download images, and save the research locally for analysis.
Why use it?
A single keyword search can miss saved material or return too many weak matches. This skill broadens the search, removes duplicates, ranks results, and converts selected article content into readable Markdown.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jtsang4/efficient-coding/cubox-research
Any agent
npx skills add jtsang4/efficient-coding --skill cubox-research
Clone the repo
git clone --depth 1 https://github.com/jtsang4/efficient-coding

Made for: Claude Code, Codex.

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00077 $0.01399
Opus 5 $0.00039 $0.00700
Sonnet 5 $0.00015 $0.00280
Haiku 4.5 $0.00008 $0.00140

Measured 2d ago against content hash e9898b06faea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cubox-research 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/cubox.ts, scripts/inspect-har.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/cubox-research/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cubox-research

Use this skill when the user's Cubox collection is the source of truth. The goal is not to do one shallow keyword lookup, but to search broadly, vary keywords on purpose, fetch the best-matching article details, and analyze local Markdown instead of raw Cubox HTML.

Preflight

  1. Work from this skill directory.
  2. Make sure dependencies are installed once with bun install.
  3. Check .env before any API call. The only required value is CUBOX_AUTHORIZATION.
  4. Prefer read-only endpoints. Do not call mutation endpoints such as POST /c/api/norm/card/read unless the user explicitly asks for that side effect.

What The Bundled Scripts Do

  • scripts/cubox.ts context Fetches account search context: groups, tags, and the overloaded keyword/list payload.
  • scripts/cubox.ts search Runs multiple keywords across preview, quick, and full-text modes, then deduplicates and ranks hits.
  • scripts/cubox.ts research Does the same search workflow and also fetches article details for the strongest matches.
  • scripts/cubox.ts fetch-detail Fetches one Cubox article detail, converts the HTML fragment to Markdown, downloads images locally, and stores the files in the temp collection.
  • scripts/inspect-har.ts Re-summarizes a HAR file into a quick API map when the user provides a fresh capture.

Core Working Style

Treat Cubox retrieval like library research:

  1. Understand the user's actual topic or question.
  2. Build a keyword set with deliberate variation.
  3. Search in more than one mode.
  4. Fetch article details for the best candidates.
  5. Analyze the exported Markdown and cite local file paths.

Do not stop after the first hit unless the user explicitly wants a quick lookup.

Keyword Planning

Before searching, create a keyword set that covers multiple angles:

  • The direct topic phrase
  • Synonyms or alternate wording
  • English and Chinese variants when relevant
  • Product names, author names, company names, or framework names tied to the topic
  • Abbreviations and shorthand terms
  • Narrower subtopics if the topic is broad

Read the full file on GitHub · 185 lines

Files

What ships with it

8 files 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.

Changes

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.

  1. 2d ago First seen · 185 lines · 77 tokens per session scan A e9898b06faea

Subscribe to this mod's changes

cubox-research is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 7d ago), licensed MIT. It adds 77 tokens to every session and 1,399 once invoked, about $0.0004 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.