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-human-reviewgit 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-human-review)<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-human-review"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-human-review/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-human-review"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-human-review.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 | $0.01317 |
| Opus 5.5 | $0.00024 | $0.00527 |
| Sonnet 5.5 | $0.00012 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
paper-human-review 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Human Review — 对话式交互 + 异步状态机
概述
本 Skill 拦截边缘分数(4-6 分)论文,生成信息卡片供人工审阅。支持两种交互模式:
- 对话式实时交互(Agent 编排模式首选):Agent 在对话中展示卡片 → 用户回复 accept/reject → Agent 调用
--chat-decide - 异步状态机(cron 场景兜底):脚本生成卡片后挂起 → 用户异步编辑 JSON →
--merge恢复
⚠️ 关键规则
- 对话式交互优先:在对话中,Agent 应展示审阅卡片并收集用户决策,不挂起 Pipeline。
- 异步不阻塞:cron 场景下脚本生成卡片、写入等待状态后立即 Exit 0 退出。
- 三模式脚本:
--init(生成卡片)、--chat-decide(对话式决策)、--merge(文件式决策)。 - 无边缘论文时跳过:如果没有边缘论文,直接复制高分论文到输出。
工作流程
对话式交互流程(Agent 编排模式首选)
Step 1: 初始化审阅
python $PAPER_AGENT_ROOT/scripts/human_review.py --init --run-id {run_id}
脚本返回 JSON,其中 compact_cards 字段包含适合对话展示的精简卡片。
Step 2: Agent 展示卡片
在对话中将 compact_cards 内容展示给用户,示例:
发现 3 篇边缘论文需要您判断:
📄 [1] (5pts) Semantic ID Generation for Recommendation
ID: 2603.01234 [generative_rec, semantic_id]
This paper proposes a novel approach to generate semantic...
📄 [2] (4pts) Collaborative Filtering with Transformers
ID: 2603.05678 [collaborative_filtering]
We present a transformer-based collaborative filtering...
请回复 accept/reject 决定,例如:
"accept 1, reject 2"
或 "accept all" / "reject all"
Step 3: 收集用户决策
等待用户回复。用户可能以多种方式回复:
- "accept 1, reject 2, accept 3"
- "accept 论文A, reject 论文B"
- "accept all"
- "reject all"
Step 4: Agent 解析决策并调用脚本
将用户回复解析为标准 JSON 格式,调用:
python $PAPER_AGENT_ROOT/scripts/human_review.py --chat-decide '[{"arxiv_id":"2603.01234","decision":"accept"},{"arxiv_id":"2603.05678","decision":"reject"}]' --run-id {run_id}
脚本将合并高分论文与捞回论文,输出 skill3_final_selection.json。
异步状态机流程(cron 场景兜底)
默认模式 — 生成卡片并挂起
python $PAPER_AGENT_ROOT/scripts/human_review.py --init --run-id {run_id}
脚本将:
- 从
skill2_scored_results.json读取边缘区论文 - 生成信息卡片(Markdown 文件 + stdout 精简格式)
- 输出
skill3_review_pending.json - 如果在 cron 模式,更新
pipeline_state.json为waiting_for_human - 尝试通过 webhook 通知用户
- Exit 0 退出,不阻塞
用户异步审阅
用户创建 skill3_human_decisions.json:
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 · 143 lines · 61 tokens per session scan A 498e71cc6f88
paper-human-review 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 1,317 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-human-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paper-human-reviewAkaliKong/PaperClaw | Skill | 22 | 8mo ago | MIT | A | 61 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |