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-knowledge-syncgit 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-knowledge-sync)<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-knowledge-sync"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-knowledge-sync/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-knowledge-sync"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-knowledge-sync.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 | $0.00061 | $0.00842 |
| Opus 5.5 | $0.00024 | $0.00337 |
| Sonnet 5.5 | $0.00012 | $0.00168 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
paper-knowledge-sync 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 2mo 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
Paper Knowledge Sync — Knowledge Base & Idea Generation
你负责将论文分析结果沉淀到持久化知识库，并基于跨论文洞察生成研究 Idea。
⚠️ 关键规则
- 在干净 Session 中执行：Idea 生成需要充足上下文窗口，通过
sessions_spawn在全新 Session 中执行。 - Agent 生成 Idea：知识同步是确定性脚本完成的，但 Idea 生成是你（Agent LLM）的核心价值。
- 结合 SOUL 文件：Idea 生成时参考
seed_papers.json+paper_index.json+ 用户研究方向。
执行流程
Step 1: 知识同步（确定性脚本）
将 skill4/skill5 产出同步到全局 paper_index.json：
python $PAPER_AGENT_ROOT/scripts/knowledge_sync.py --sync --run-id {run_id}
返回同步统计：
{
"total_indexed": 42,
"new_count": 5,
"updated_count": 0,
"with_code": 18,
"with_relations": 12
}
Step 2: 准备 Idea 生成上下文
python $PAPER_AGENT_ROOT/scripts/knowledge_sync.py --prepare-ideas --run-id {run_id}
脚本生成 pipeline_data/{run_id}/skill6_idea_context.json，包含：
- 用户研究方向描述
- 种子论文关键信息
- 本次新增论文摘要
- 所有可迁移技术列表
- Idea 生成 prompt
Step 3: Agent LLM 生成 Idea（你来做）
请读取 pipeline_data/{run_id}/skill6_idea_context.json，使用其中的 prompt 生成 2-3 个研究 Idea 提案。
每个 Idea 需包含：
- Title：简洁描述性标题
- Motivation：为什么值得做（1-2 句）
- Key Insight：跨论文洞察是什么
- Approach：高层方法论（2-3 句）
- Feasibility：Low / Medium / High + 简要理由
- Related Papers：灵感来自哪些论文
Step 4: 保存 Idea
将生成的 Idea 文本传回脚本保存：
python $PAPER_AGENT_ROOT/scripts/knowledge_sync.py \
--save-ideas --run-id {run_id} \
--ideas-text "## Idea 1: ...\n\n## Idea 2: ..."
Idea 保存到 ideas/{date}_idea_proposal.md。
论文关联检测
知识同步时自动检测新论文与已有论文的关联：
| 关联类型 | 说明 |
|---|---|
same_subfield |
同一研究子领域 |
shared_baselines |
共享对比基线 |
shared_techniques |
共享可迁移技术 |
same_authors |
共同作者 |
关联关系存储在 paper_index.json 的 relations 字段中。
输出文件
| 文件 | 说明 |
|---|---|
paper_index.json |
全局论文知识库索引（持久化） |
skill6_idea_context.json |
Idea 生成上下文（per-run） |
ideas/{date}_idea_proposal.md |
研究 Idea 提案（持久化） |
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.
- 2mo ago First seen · 102 lines · 61 tokens per session scan A 038f0aaeb9bc
paper-knowledge-sync is a skill published in the GitHub repository AkaliKong/PaperClaw (22 stars, last pushed 8mo ago), licensed MIT. It adds 61 tokens to every session and 842 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 2026-08-30.
paper-knowledge-sync compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paper-knowledge-syncAkaliKong/PaperClaw | Skill | 22 | 8mo ago | MIT | A | 61 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |