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 AkaliKong/PaperClaw --skill paper-pipelinegit clone --depth 1 https://github.com/AkaliKong/PaperClawWrote 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/akalikong/paperclaw/paper-pipeline)<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-pipeline"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-pipeline/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/akalikong/paperclaw/paper-pipeline"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-pipeline.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 | $0.00085 | $0.02125 |
| Opus 5 | $0.00043 | $0.01063 |
| Sonnet 5 | $0.00017 | $0.00425 |
| Haiku 4.5 | $0.00009 | $0.00213 |
Grade A, and why
paper-pipeline 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 11d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Pipeline — Agent 分步编排(Path B)
你是论文阅读 Pipeline 的编排者和大脑。你将按以下步骤逐个调用脚本工具完成完整流程,并在需要 LLM 智能的环节(评分、精读、Idea 生成)直接用自身能力完成。
⚠️ 关键规则
- 你是编排者:按下方步骤依次执行,每步检查返回结果后再进行下一步。
- 数据通过文件系统传递:所有中间数据存放在
pipeline_data/{run_id}/目录下,禁止在对话上下文中传递大量数据。 - 结构化 JSON 输出:每个脚本调用都返回 JSON,你需要解析
status字段判断成功/失败。 - 断点续跑:如果用户说"继续之前的巡检",先执行
--status查看进度,从未完成的步骤恢复。
首次运行 — "开始论文日常巡检"
Step 0: 初始化 Pipeline
python $PAPER_AGENT_ROOT/scripts/pipeline_runner.py --step init
记录返回的 run_id,后续所有步骤都使用此 run_id。
Step 1: 种子初始化 + 论文搜索
python $PAPER_AGENT_ROOT/scripts/pipeline_runner.py --step seed+search --run-id {run_id}
检查返回结果中的搜索统计。如果 search_new_increment 为 0,告知用户"本次没有新增论文"并跳到 Step 7 生成摘要。
Step 2: 准备评分上下文
python $PAPER_AGENT_ROOT/scripts/pipeline_runner.py --step prepare-scoring --run-id {run_id}
脚本会生成 skill2_scoring_context.json,包含待评分论文列表和 few-shot 校准示例。
Step 3: Agent LLM 评分(你来做)
请读取 pipeline_data/{run_id}/skill2_scoring_context.json 文件内容。
根据文件中的评分提示(prompt)和 few-shot 校准示例,对每篇论文进行 0-10 分的相关性评分。
评分维度:
- 与用户研究方向(参见 profile.yaml 中的 research_description)的直接相关度
- 方法论创新性
- 与核心论文(seed_papers.json 中 role 为 foundational 的论文)的技术关联度
- 潜在实验价值
输出要求 — 极其重要:
将评分结果以纯 JSON 数组写入 pipeline_data/{run_id}/skill2_agent_raw_output.json。
格式:
[
{
"arxiv_id": "2603.01234",
"relevance_score": 8,
"scoring_rationale": "该论文提出了与用户研究方向高度相关的新方法...",
"tags": ["relevant_method", "novel_approach"]
}
]
禁止:Markdown 修饰符、寒暄语、解释性文字。仅输出纯 JSON。
Step 4: 后处理评分结果
python $PAPER_AGENT_ROOT/scripts/pipeline_runner.py --step postprocess-scoring --run-id {run_id}
脚本会解析你的评分输出、应用白名单/顶会加分、按评分排序分三区(高分/边缘/低分)。
向用户报告打分统计:高分 M 篇、边缘 K 篇、低分 L 篇。
Step 5: 人工审阅(对话式交互)
python $PAPER_AGENT_ROOT/scripts/pipeline_runner.py --step human-review-init --run-id {run_id}
如果返回 skipped: true(无边缘论文),直接跳到 Step 6。
如果返回 waiting_for_human: true,将 compact_cards 字段的内容展示给用户,请求审阅。
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.
- 11d ago First seen · 204 lines · 85 tokens per session scan A db4a649e054a
paper-pipeline is a skill published in the GitHub repository AkaliKong/PaperClaw (22 stars, last pushed 6mo ago), licensed MIT. It adds 85 tokens to every session and 2,125 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…