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 volcengine-sdk-generatorgit 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/volcengine-sdk-generator)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/volcengine-sdk-generator"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/volcengine-sdk-generator.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 5.1 | $0.00256 | $0.06180 |
| Opus 5 | $0.00128 | $0.03090 |
| Sonnet 5 | $0.00051 | $0.01236 |
| Haiku 4.5 | $0.00026 | $0.00618 |
Grade A, and why
volcengine-sdk-generator 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 3d 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 — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Volcengine SDK Code Generator
Generate complete, runnable Volcengine SDK code from natural-language descriptions, and answer SDK configuration questions.
Workflow
When a user describes a Volcengine API operation, follow these steps:
Step 1: Identify Target Service, Operation, and Advanced Configuration Needs
Parse the user's description to determine:
-
Target service: which Volcengine service (e.g., ECS, VPC, TOS, billing)
-
Target operation: what operation to perform (e.g., list instances, create a VPC, query billing)
-
Target language: which programming language (Go, Python, PHP, Java, Node.js). If not specified, ask the user.
-
Advanced configuration needs: whether the user mentions or the scenario implies any of the following:
- Retry: user mentions "retry", "fault tolerance", or the operation is a write/create type (prone to throttling)
- Timeout: user mentions "timeout", or the operation involves large data volumes (batch queries, file uploads)
- Credentials: user mentions "STS", "AssumeRole", "temporary credentials", "OIDC", or explicitly wants to avoid hardcoding AK/SK
- Proxy/network: user mentions "proxy" or "internal network"
- Debug mode: user mentions "debug" or "logging"
- Connection pooling: user mentions "connection pool", "high concurrency", or "pool"
If the user explicitly requests these, include the corresponding configuration in the generated code. If not explicitly requested but implied by the scenario (e.g., resource creation naturally warrants retry), include suggested configuration as comments.
Step 2: Query Service Metadata via Volcengine API Explorer
Use the following APIs to find the correct service code, version, and action name. This step is critical because guessing often produces incorrect code — the API Explorer is the authoritative source.
2a. Find the ServiceCode
Fetch the service catalog:
GET https://api.volcengine.com/api/common/explorer/services
Response structure:
{
"Result": {
"Categories": [
{
"CategoryName": "...",
"Services": [
{
"ServiceCn": "Cloud Server",
"ServiceCode": "ecs",
"Product": "ECS",
"IsSdkAvailable": true,
"RegionType": "regional"
}
]
}
]
}
}
Match the user's intent to the correct ServiceCode based on ServiceCn, Product, and category name.
What ships with it
6 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.
- 3d ago First seen · 578 lines · 256 tokens per session scan A 2b891cc854c2
volcengine-sdk-generator is a skill published in the GitHub repository bytedance/agentkit-samples (449 stars, last pushed 3d ago), licensed Apache-2.0. It adds 256 tokens to every session and 6,180 once invoked, about $0.0013 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
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
blind-sqli
Blind SQL injection under hostile WAF — manual bypass playbook for when sqlmap fails because common tokens (SUBSTRING, IF, AND, WHERE, single quotes) are filtered. Covers token-fingerprinting probe loops, arithmetic-multiplication boolean evaluation, hex-encoded literals, and exponential-probe binary search. Loaded on…
graphql
GraphQL exploitation — introspection, injection, authorization bypass, and data exfiltration through GraphQL APIs.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
golang-graphql
Implements GraphQL APIs in Golang using gqlgen or graphql-go. Apply when building GraphQL servers, designing schemas, writing resolvers, handling subscriptions, or integrating GraphQL with existing Go HTTP services. Also apply when the codebase imports github.com/99designs/gqlgen or github.com/graph-gophers/graphql-go.
golang-grpc
Provides gRPC usage guidelines, protobuf organization, and production-ready patterns for Golang microservices. Use when implementing, reviewing, or debugging gRPC servers/clients, writing proto files, setting up interceptors, handling gRPC errors with status codes, configuring TLS/mTLS, testing with bufconn, or…