bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 bytedance/agentkit-samples --skill byted-volcengine-topology-change-impactgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/byted-volcengine-topology-change-impact)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-volcengine-topology-change-impact"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-volcengine-topology-change-impact/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/bytedance/agentkit-samples/byted-volcengine-topology-change-impact"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-volcengine-topology-change-impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.02261 |
| Opus 5 | $0.00059 | $0.01130 |
| Sonnet 5 | $0.00024 | $0.00452 |
| Haiku 4.5 | $0.00012 | $0.00226 |
Grade A, and why
byted-volcengine-topology-change-impact 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 7d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
变更风险分析 Skill
能力定位
这个 Skill 负责把“变更描述”转成一份可执行的静态风险分析结果。
- 输入通常是自然语言变更单,也可以是简短的代码/配置变更说明
- 分析基础是已有的
topology.json,不是运行时监控或实时健康状态 - 关注三类结果:风险等级、影响范围、上下游影响描述
- 第一版优先覆盖“服务/组件”和“云资源”两类对象
这个 Skill 不直接构建拓扑;如果当前工作区还没有 business_topologies/<business>/topology.json,应先使用 topology-graph-builder 生成底层数据。
依赖:本 Skill 只需要 topology-graph-builder 生成的 topology.json 作为数据输入。同时依赖 references/risk_assessment_rules.md 中的指南进行风险推断。
输入前提
默认在当前工作区寻找:
business_topologies/
<business>/
topology.json
topology.md
如果工作区中存在 .trae/business_topologies/,也可以直接复用。
静态风险分析的前提是:用户至少提供下面两类信息中的大部分。
- 变更动作:例如“修改配置”“开放 80 端口”“把副本数从 4 缩到 2”“切换入口 CLB”
- 变更对象:例如服务名、组件名、ECS、CLB、EIP、安全组、子网、VPC
如果用户只说“帮我评估这个变更”,但没有说明目标对象,要先追问。
标准流程
1. 提炼变更卡片
先把用户输入整理成一张简化的变更卡片:
change_type:代码变更 / 配置变更 / 扩容 / 缩容 / 网络策略 / 入口切换 / 其他target:目标服务、组件或云资源action:新增 / 删除 / 修改 / 替换 / 放开 / 收紧 / 扩 / 缩scope:如果用户给了业务、环境、地域,要一并带上assumption:缺失信息要显式标记为假设
如果用户给的是代码变更或配置变更,但没有直接出现资源 ID,要先抽取最可能的服务名、组件名、应用名、网关名、配置项名或资源关键词,再去拓扑里做候选匹配。
2. 优先用脚本做结构化分析
不要直接肉眼扫 topology.json。优先执行当前 Skill 自带的脚本:
python3 ./skills/byted-volcengine-topology-change-impact/scripts/change_risk_from_topology.py \
--node "<target>" \
--output markdown
其中 --node 是变更目标。脚本只负责查询出结构化的拓扑数据和受影响的 ECS。
如果用户已经明确给了业务:
python3 ./skills/byted-volcengine-topology-change-impact/scripts/change_risk_from_topology.py \
--business "<business>" \
--node "<target>" \
--output markdown
脚本内部直接读取 topology.json 进行节点匹配和图分析,自动拿到:
- 命中目标和基础信息
- 受影响的下游 ECS
- 关联资源和入口链路
- 文字化的上下游结构描述
3. 阅读指南并由大模型推断风险
核心要求:脚本不会输出任何“风险等级”或“风险结论”。你(大模型)必须:
- 阅读本 skill 目录下的
references/risk_assessment_rules.md。 - 结合用户的原始变更描述(动作)和脚本输出的结构化数据(受影响资源),基于指南中的原则,自主推理出本次变更的风险等级、风险结论和影响边界。
4. 多候选时先控风险
如果返回多个候选:
id:exact、public_ip:exact这类高置信命中,可以以第一候选为主继续分析- 如果只是
name:fuzzy、metadata:fuzzy,先把候选列表给用户确认 - 如果服务名和资源名混在一起,要明确说明“当前是基于拓扑字段和元数据做静态匹配”
不要在低置信命中下直接下结论。
回答原则
1. 先结论,再证据
What ships with it
2 files 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.
- 7d ago First seen · 230 lines · 118 tokens per session scan A de819e162692
byted-volcengine-topology-change-impact is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 2,261 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.