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/volcengine/ark-cli/arkcli-resourcesnpx skills add volcengine/ark-cli --skill arkcli-resourcesgit clone --depth 1 https://github.com/volcengine/ark-cliWhat 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 | $0.00079 | $0.02291 |
| Opus 5 | $0.00039 | $0.01145 |
| Sonnet 5 | $0.00016 | $0.00458 |
| Haiku 4.5 | $0.00008 | $0.00229 |
Grade A, and why
arkcli-resources 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli resources
CRITICAL — 开始前 MUST 先用 Read 工具读取 ../arkcli-shared/SKILL.md，其中包含认证闸门、配置排查与命令选择顺序
使用原则
arkcli resources域始终只读。即使用户在资源列表语境中提出创建意图，也必须先转读../arkcli-deploy/SKILL.md，不能由本 Skill 创建、修改或删除资源- 普通“部署模型并获得 Endpoint”的产品意图继续走
arkcli +deploy。该在线工作流不支持 Client Preview，不得执行arkcli +deploy --dry-run，也不得为了获得 Preview 而静默降级成底层 CRUD - 转入 Deploy Skill 后，先只读核对模型、名称、Region、配置与计费影响并复述给用户；在收到本轮新的明确确认前，不得在同一轮执行真实
arkcli +deploy。严禁 Agent 自行添加--yes、echo Y或设置ARKCLI_ALLOW_HEADLESS_ACTIVATION - 只有用户明确要求 raw CRUD、精确 CreateEndpoint 请求或 CI/脚本预览时，才转
../arkcli-infer-endpoint/SKILL.md，使用叶子命令arkcli infer endpoint create ... --dry-run；Preview 完成后仍需新的确认才能真实执行 arkcli resources list是 read-only 实时控制面查询，每次都打上游，没有本地缓存arkcli resources resolve <ep-id>先按endpoint_model_type判定真实绑定。Custom Model Endpoint 的model_id/custom_model_id必须保持cm-...身份，基础模型只通过base_model_*表达 lineage 与能力来源；不按 ID/模型名子串猜用途- 派发逻辑跟 profile.Type 走：platform →
ListEndpoints，agent-plan / coding-plan → 对应 plan API agent-plan-team三模态使用团队席位 Key + 套餐模型；coding-plan-team只有 text 使用团队席位 Key，image/video 虽可看到 platform Endpoint，但调用还需要后付费 API Keyresources list区分“账号可见”与“当前 profile 可调用”：读取invocable与required_overrides，不要看到 ID 就断言当前凭证可用- 这个 skill 不负责改 default —— 用户要换 default 走
../arkcli-profile/SKILL.md的profile set-default --profile X真切身份（P0-A 修正）：用 X 的 token / UserID 打控制面，不是 active=A 的身份打完再展示成 B 的资源
适用场景
- 用户问"当前 profile 下有哪些 endpoint / 模型可用"
- 用户跑
profile set-default时报<id> 不在可用列表，回这里看真实可用 ID - 用户跑
+chat / +gen --model报InvalidEndpointOrModel.NotFound，回这里确认 ID 在 active profile 下可见 - 用户切了 profile，想知道新 profile 下的可用资源跟旧的有什么差异
- 用户只给出一个 Endpoint，不知道该走
+chat、+understand还是+gen - 用户传了 Endpoint + API Key，但未给 Base URL，需要从 Endpoint 权威 region 派生
反唤起信号
- 用户要 找模型 / 挑模型 / "哪个模型最强 / 性价比最高" → 转
../arkcli-models/SKILL.md（带 enrich + 加权排序） - 用户要 创建 endpoint → 转
../arkcli-deploy/SKILL.md（arkcli +deploy）；本轮只做只读核对、复述和确认，不直接执行 - 用户明确要 raw CreateEndpoint / CI / 精确请求预览 → 转
../arkcli-infer-endpoint/SKILL.md，使用infer endpoint create --dry-run - 用户要 管理 endpoint（start / stop / get / update / list 详情）→ 转
../arkcli-infer-endpoint/SKILL.md
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.
- 2d ago First seen · 116 lines · 79 tokens per session scan A f5c5fa7b5103
arkcli-resources is a skill published in the GitHub repository volcengine/ark-cli (112 stars, last pushed 5d ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,291 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
high-perf-browser
Optimize web performance through network protocols, resource loading, and browser rendering internals. Use when the user mentions "my site is slow", "Core Web Vitals", "HTTP/2 or HTTP/3", "resource hints", "network latency", "render blocking", "TCP/TLS optimization", "service worker", "Cache-Control or caching…
asc-app-create-ui
Create a new App Store Connect app record via browser automation. Use when there is no public API for app creation and you need an agent to drive the New App form.
2026-legal-research-agent
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic…
grill-me-qa
A guided interview to challenge and validate QA automation plans, test strategies, and framework designs before implementation. Use when the user wants to validate a test architecture, challenge a testing decision, prepare an AI-assisted testing rollout, or uses any "grill" trigger phrase (grill my test plan, audit my…
a11y-playwright-testing
Accessibility testing for web applications using Playwright (@playwright/test), TypeScript, and axe-core. Use to write, run, or debug WCAG 2.2 AA checks, keyboard and focus tests, ARIA/semantic validation, accessible names, form labels, color contrast, or screen-reader test patterns. Keywords: accessibility, WCAG…
accessibility-selenium-testing
Accessibility testing toolkit using Selenium WebDriver 4+ with Java 21+ and axe-core engine. Use when asked to validate WCAG 2.2 AA compliance, scan pages or components for a11y violations, test keyboard navigation, audit color contrast, check ARIA semantics, generate accessibility reports, filter axe rules, debug…