curate-research

curate-research is a skill for Claude Code from deusyu/harness-engineering. It costs 116 tokens per session (2,434 once invoked), scanned A, original, MIT.

A workflow for processing research candidates such as articles, papers, and tools, then translating, reviewing, and possibly adding them to a knowledge repository. It includes a human approval step before publication.

In plain words
What is it for?
Fetching source pages, creating translations and review files, recording publication candidates, adding approved items to the repository, checking consistency, and cleaning up temporary files.
Why use it?
It organizes the many steps involved in turning web research into checked, tracked documents. The approval gate helps prevent unreviewed material from being added.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

About the project

deusyu/harness-engineering is a learning archive about designing repositories, rules, tools, and feedback loops so AI coding agents can work reliably. It is for engineers studying and practicing this approach to agent-assisted software development. Its catalogue entries package parts of the project’s guidance as an agent skill and instruction.

deusyu/harness-engineering · 5,803 stars · on GitHub

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/deusyu/harness-engineering/curate-research
Any agent
npx skills add deusyu/harness-engineering --skill curate-research
Clone the repo
git clone --depth 1 https://github.com/deusyu/harness-engineering

Made for: Claude Code.

Wrote 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.

agentmods badge for curate-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/deusyu/harness-engineering/curate-research.svg)](https://agentmods.dev/skills/deusyu/harness-engineering/curate-research)
Your own site
<a href="https://agentmods.dev/skills/deusyu/harness-engineering/curate-research"><img src="https://agentmods.dev/badge/skills/deusyu/harness-engineering/curate-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00116 $0.02434
Opus 5 $0.00058 $0.01217
Sonnet 5 $0.00023 $0.00487
Haiku 4.5 $0.00012 $0.00243

Measured 6d ago against content hash f098d6151ae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

curate-research scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- [ ] **数图要抓原文 HTML 数,不能只看渲染出来的正文。** 2026-07-27 的教训:一篇 claude.com 译文声明 `sourceFigureCount: 0`,而原文 HTML 里有 4 个 `<figure>`——抓取工具吐出的 markdown 把它们丢了,人只看那份 markdown 就会以为没有图。可用 `curl <url> | grep -c '<figure'` 交叉验证
.claude/skills/curate-research/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

curate-research —— 仓库自我策展 harness

一个讲 Harness Engineering 的仓库,用一个 harness 来策展自己。本 skill 把外部调研候选可控地整合进 tracked 档案。

核心约束:评审全自动;收录是人类闸门,必须停下来和用户来回讨论后才动 works/articles.md

何时用

  • 用户给出一批候选 URL(文章 / 论文 / 工具 / 项目),希望整合进仓库
  • 用户说「处理 / 收录 / 整理」translate/ 暂存区的翻译
  • 已有 translate/<batch>/works-ready/ 候选译文,要决定去向

输入与产物路径

暂存区(gitignored,本地过程区):translate/<batch>/

  • sources/<slug>/source.md(原文快照;论文额外抓 source-full.md
  • translations/<slug>/{01-analysis,02-prompt,translation}.md(过程三件套)
  • works-ready/<slug>-translation.md(发布候选)+ works-ready/README.md(状态表,本批权威)

正式档案(tracked):works/<slug>-translation.md + references/articles.md 条目。

流水线 6 阶段

①抓取 ──②翻译 ──③评审[全自动] ──🚧人类闸门🚧──④收录 ──⑤校验 ──⑥清理

① 抓取

baoyu-url-to-markdown 把每个 URL 存到 sources/<slug>/source.md论文/长文必须额外抓 HTML 全文到 source-full.md(否则只有摘要页,C8 会拦谎报)。

② 翻译

按 baoyu-translate 配置生成 translations/<slug>/ 三件套 → works-ready/<slug>-translation.md01-analysis.md 要含收录建议;source-full.md 存在时,分析稿不得声称「仅摘要页」。

③ 评审(全自动并行扇出)

对每篇候选派一个评审 agent(一批 3–4 篇,并行多个 agent)。统一打分维度,吐结构化定性。标准评审 prompt 模板:

你是 Harness Engineering 中文知识库的内容评审。仓库主题:人类设计约束与反馈回路、AI agent 写代码。 读 sources/<slug>/source.md(+source-full.md)、works-ready/<slug>-translation.mdtranslations/<slug>/01-analysis.md,逐篇回答:

  • 原文价值:原创洞察密度 / 长文实质 vs 产品页·发布稿·摘要。高/中/低
  • 翻译质量:完整逐译 / 压缩摘要 / 首轮粗稿;通顺度、术语到位度。精品/合格/需返工
  • 与仓库契合度:补薄弱环节还是重复
  • 一句话定性 + 建议去向:works/ 正式收录 / articles.md 观察项一行 / tools/ / 暂不收录 基于实际内容,紧凑中文,结构化输出即为最终产出。

汇总成一张「候选 × 定性 × 去向」表。

🚧 人类闸门(不可跳过)

把评审表交给用户,来回讨论收录决策。精品 vs 边角的边界判断、是否返工、哪些合并成专题——都由人定。未经用户确认,不得进入 ④。

④ 收录(按减熵分流规则)

  • 实质原创长文 / 论文 → works/cpworks/<slug>-translation.md,在 articles.md 加一个 ### N. 编号条目(脉络一末尾,旧编号顺移),并同步全部计数缓存(见下)。
  • 边角材料(产品页 / README / 发布稿 / 短 bliki)→ articles.md「观察项 / 候选材料(不计入文章数)」表一行,链上游 URL,不做编号条目(文章数不变)。
  • 工具类 → 只在用户实际用过后才进 tools/;未实测前在观察项表标 🔵「待实测后入 tools/」。
  • 需返工的长文:先润色(事实核查加译者注 / 术语统一)再进 works/

Read the full file on GitHub · 98 lines

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. 6d ago First seen · 98 lines · 116 tokens per session scan A f098d6151ae8

Subscribe to this mod's changes

curate-research is a skill published in the GitHub repository deusyu/harness-engineering (5,803 stars, last pushed 9d ago), licensed MIT. It adds 116 tokens to every session and 2,434 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens