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 gy910210/hermes-research-skills --skill paper-critic-zhgit clone --depth 1 https://github.com/gy910210/hermes-research-skillsWrote 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/gy910210/hermes-research-skills/paper-critic-zh)<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/paper-critic-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/paper-critic-zh/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/gy910210/hermes-research-skills/paper-critic-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/paper-critic-zh.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 | $0.00067 | $0.00654 |
| Opus 5 | $0.00034 | $0.00327 |
| Sonnet 5 | $0.00013 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
paper-critic-zh 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 12d 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
Hermes 适配说明
- 本 skill 现面向 Hermes 使用，优先依赖 Hermes 原生工具：
search_files、read_file、write_file、patch、session_search、delegate_task、cronjob、browser、web/search、vision。 - 若正文提到
references/...或scripts/...，优先读取当前 skill 目录下对应文件，不再依赖 Claude 专属目录结构。 - 原始 Claude
agents/openai.yaml不作为执行前提；需要并行研究、分工精读或角色评审时，改用 Hermes 的delegate_task。 - 保留原有研究方法论与产物契约，但执行层统一按 Hermes 工具体系落地。
Paper Critic（中文）
输入
paper_notes（推荐）evidence_map（可选）existing_claims或拟写结论（可选）
输出
evidence_audit- 字段契约见
../research-orchestrator-zh/references/artifact-contracts.md
- 字段契约见
步骤
- 对每条拟写结论判断它属于
直接证据、邻近证据还是综合判断。 - 检查是否存在常见过度推理：
- 从 offline 指标推出 online gain
- 从模拟器推出真实用户迁移
- 从 demo 推出可部署
- 从行业报道或产品观察推出平台内部结论
- 从单个入口形态推出底层技术路线已经成立
- 对 benchmark、release、私有数据、license、未披露规模等信息做事实性审校。
- 若来源包含行业报道、采访、产品观察或二手传闻，补充一层
publicly_verifiable / industry_observation / rumor_or_unverified标注。 - 对每个子方向产出：
strongest_supportstrongest_contradictionstill-missing evidencerisky wording to avoid
- 给出可直接用于改写主稿的
rewrite_suggestions。
守护
- 所有审校意见都要能回指到原始来源。
- 审校器不是为了“挑刺”，而是为了把结论写稳。
- 不能确认的事实应降级为
未披露或待验证。 - 对产业侧信息，优先区分“官方页面可确认”“高质量报道可观察”“内部说法不可证实”三层。
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.
- 12d ago First seen · 45 lines · 67 tokens per session scan A a28ac4313c92
paper-critic-zh is a skill published in the GitHub repository gy910210/hermes-research-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 654 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
b2b-sdr-agent
Autonomous AI Sales Development Rep for B2B export — handles lead discovery, BANT qualification, multi-channel outreach (WhatsApp/Email/Telegram), CRM management, and deal pipeline tracking. Built for cross-border trade.
loop-engineering
Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step.
fablize
A harness that makes any model see a task through to the end — with evidence and verification — as procedure, not as luck. Enforces verification grounding (run & observe artifacts before declaring done), multi-story decomposition with an evidence gate, a systematic investigation protocol, and early-stop prevention.…
browser-harness-ats-automation
Automate job applications on ATS platforms (Ashby, Greenhouse, Workday) using browser-use/browser-harness with CDP. Covers iframe session management, file upload, hidden checkbox handling, and known reCAPTCHA/S3 blockers.
job-scraper-pipeline
Automated ML/AI job scraping, deduplication, and gatekeeper scoring pipeline. Scrapes AI company career pages on Greenhouse, AshbyHQ, and Lever, avoids duplicates, and scores jobs 0-100 against profile keywords, classifying tier-1/2/3.
greenhouse-job-application
Automate filling job applications on Greenhouse.io and similar React-based ATS platforms via browser automation. Covers React input handling, reCAPTCHA detection, resume upload limitations, and single-expression multi-field filling.