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 agentmods add skills/tencentcloud/octop/source-verifynpx skills add TencentCloud/Octop --skill source-verifygit clone --depth 1 https://github.com/TencentCloud/OctopWrote 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/tencentcloud/octop/source-verify)<a href="https://agentmods.dev/skills/tencentcloud/octop/source-verify"><img src="https://agentmods.dev/badge/skills/tencentcloud/octop/source-verify.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.04184 |
| Opus 5 | $0.00040 | $0.02092 |
| Sonnet 5 | $0.00016 | $0.00837 |
| Haiku 4.5 | $0.00008 | $0.00418 |
Grade A, and why
source-verify 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 4d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
统一信源核验
路由边界
纯粹判断文件是否为权威原文、是否最新有效以及修订/替代/废止关系时，只使用本技能及下方【信源核验】模板，不再调用 output-format skill 或 ../../scripts/validate_output.py。如果用户还要求生成指南学习内容，先完成信源核验，再把已核验来源交给对应医学学习 skill，并只对学习内容执行 output-format 校验。
先选择核验档位
快速核验（默认）
适用于普通教育性医学问答、概念解释、常见误区澄清和一般学习摘要，且不涉及下方完整核验触发项。
- 目标是取得 1 份足以覆盖问题的现行权威规范性正文；不得主动搜集多份文件相互“佐证”。
- 最小核对项为：权威机构/正式发布域、规范性文档类型、完整标题、发布机构、年份/版本、正文能够支持本次主张。
- 官方原文页已明确上述身份时，不强制另找第二来源；原文没有 DOI/推荐等级时如实写“未标注”，不为补字段继续搜索。
- 命中未过
recheck_after的已核验入口时，直接抓取正文并核对身份；用户未问“最新/现行/替代”时不再追加时效搜索。 - 一份文档满足身份、正文与覆盖范围后立即停止。
完整核验（按需升级）
出现以下任一情形时才升级：用户明确询问最新/现行/替代/废止、跨版本变化、精确推荐或证据等级、章表页条目定位；适应症、禁忌症、剂量、孕产妇/儿童、严重不良反应、侵入/急诊内容；药品批准、监管、医保或法律状态。完整核验保留版本状态、唯一标识、精确定位和必要的同文献身份核验要求。
核验档位只减少不必要的步骤，不改变“不能用二手摘要补精确临床事实”的底线。
按需读取文件
快速核验先只读取 ../../references/verified-source-entrypoints.yaml。命中即可按其直达入口抓取，不预读完整白名单和合规说明。
以下情况再读取对应文件：
- 未命中入口、需要判断域名/文档类型/B+ 或 C 级资格：
../../references/source-policy.yaml - 请求接近个体诊疗、处方或其他医学边界：
../../references/compliance-boundary.md - 目标由国内专业学会或分会发布且入口未命中：
../../references/professional-society-source-routes.yaml
以上是确定路径，直接读取；不得为定位这些文件调用 glob、grep 或递归 ls。
用户明确指定国际指南，或国内现行正式文件没有覆盖目标主题时，再读取
../../references/international-guideline-source-routes.yaml；普通国内主题不预读该表。
已核验入口的使用顺序
- 先用用户主题匹配
verified-source-entrypoints.yaml的aliases。未命中才进入常规联网检索。 - 命中时直接
web_fetch该条目的canonical_url，快速核验至少核对标题、发布机构、年份/版本和正文覆盖范围；表项提供 DOI 时再核对 DOI。完整核验中唯一标识冲突则不得使用。 - 当前日期超过
recheck_after，或用户明确询问「最新/现行/替代」时，再加 1 次限定官方域名的时效检索；没有新版正式原文证据时，不得仅凭搜索摘要改写表内版本状态。 version_relation是已核验的表述边界。它写「未取得废止/替代声明」时，必须如实输出「未证实正式废止或替代」，不得自行推断。- 命中条目的最终原文链接必须使用该条目的
canonical_url；official_index_url只用于辅助核对卷期/DOI，不得取代原文链接。全文受订阅限制时可以说明可核对范围受限，但仍要给出canonical_url。
专业学会快速路由
高频入口未命中，且目标文件由专业学会、协会或专科分会制定/发布时，直接读取
../../references/professional-society-source-routes.yaml，先按分会名称和 aliases
匹配，再进行限定域名检索；不得先做无域名的广泛搜索。
- 中华医学会分会先匹配已登记的专属
*.cma.org.cn子域；没有专属子域时，使用官方专科分会目录确认身份，再限定cma.org.cn、medjournals.cn或rs.yiigle.com检索。 conditional_final路由仍须通过正式文档类型、完整性和版本核验，域名命中本身不构成最终证据。official_discovery_pending_fulltext_acceptance路由只能定位发布信息和正式原文，不得直接进入最终来源行；必须继续取得 S/A 正式原文或完成该站点的完整文档身份验收。- 找到一份足以覆盖问题的完整现行正式文件后立即停止，不再遍历其他学会网站。
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.
- 4d ago First seen · 173 lines · 80 tokens per session scan A 080cff1e62a6
source-verify is a skill published in the GitHub repository TencentCloud/Octop (1,413 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 4,184 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
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
figure-style
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
scvi-tools
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…