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 jtsang4/efficient-coding --skill cubox-researchgit clone --depth 1 https://github.com/jtsang4/efficient-codingWrote 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/jtsang4/efficient-coding/cubox-research)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/cubox-research"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/cubox-research/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/jtsang4/efficient-coding/cubox-research"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/cubox-research.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 | $0.00077 | $0.01399 |
| Opus 5.5 | $0.00031 | $0.00560 |
| Sonnet 5.5 | $0.00015 | $0.00280 |
| Haiku 4.5 | $0.00008 | $0.00140 |
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 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.
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
- Work from this skill directory.
- Make sure dependencies are installed once with
bun install. - Check
.envbefore any API call. The only required value isCUBOX_AUTHORIZATION. - Prefer read-only endpoints. Do not call mutation endpoints such as
POST /c/api/norm/card/readunless the user explicitly asks for that side effect.
What The Bundled Scripts Do
scripts/cubox.ts contextFetches account search context: groups, tags, and the overloadedkeyword/listpayload.scripts/cubox.ts searchRuns multiple keywords acrosspreview,quick, andfull-textmodes, then deduplicates and ranks hits.scripts/cubox.ts researchDoes the same search workflow and also fetches article details for the strongest matches.scripts/cubox.ts fetch-detailFetches one Cubox article detail, converts the HTML fragment to Markdown, downloads images locally, and stores the files in the temp collection.scripts/inspect-har.tsRe-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:
- Understand the user's actual topic or question.
- Build a keyword set with deliberate variation.
- Search in more than one mode.
- Fetch article details for the best candidates.
- 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
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.
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 First seen · 185 lines · 77 tokens per session scan A e9898b06faea
cubox-research is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 77 tokens to every session and 1,399 once invoked, about $0.0003 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
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.