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 volcengine/ark-cli --skill arkcli-agentgit clone --depth 1 https://github.com/volcengine/ark-cliWrote 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/volcengine/ark-cli/arkcli-agent)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-agent"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-agent/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/volcengine/ark-cli/arkcli-agent"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-agent.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 | $0.00055 | $0.05791 |
| Opus 5.5 | $0.00022 | $0.02316 |
| Sonnet 5.5 | $0.00011 | $0.01158 |
| Haiku 4.5 | $0.00006 | $0.00579 |
Grade A, and why
arkcli-agent 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 17d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli agent
CRITICAL — 开始前 MUST 先读取 ../arkcli-shared/SKILL.md。
当用户需要创建、查询、调试或联通 ARK Managed Agent 时使用本 skill。核心原则：先用稳定产品命令，不要直接猜 OpenTOP Action；Session 运行时资源、事件、线程、Files API 走数据面直联；MCP OAuth 登录先查后端 provider，再用 arkcli agent +mcp-login。
执行前按“先选路径”读取对应 reference；只读相关 reference，不需要一次性加载全部细节。用户请求如果已经明确是创建、复制、挂文件、聊天、MCP 登录等写操作，完成必要确认/消歧后直接执行，不要只给命令建议。
创建 Agent 的最小决策表
仅咨询参数含义、命令用法或解读已有完整 stdout 时，能从文档与当前证据回答就直接回答， 不为概念解释发起 live 查询。只有账号当前配置、资源状态或模型实时可用性等问题才查服务端。 已拿到完整结果时复用它；名称搜索/grep 无命中不等于资源不存在，先确认目标是 Agent、 Environment 还是 Session。用户提供明确 ID 时直接查对应资源，不先列全量清单。
| 用户输入 | AI Agent 的处理 |
|---|---|
| 未指定 Agent 主模型 | 创建任务有自然语言意图时，用 arkcli agent model list --query "<用户意图>" --format json 完整取候选并有据择优；仅列白名单时用 arkcli agent model list --format json。明确硬指标再按具体版本查 metadata，不凭记忆拼 ID |
| 需要为工具选择绑定模型 | 用 agent model list --usage tool --format json；不默认加 --primary-only，选中的 items[].model 填入 Tools[].Configs[].Models[].ID，不修改 Agent 主模型 |
| 未指定 Skill | 先查本账号 custom skill；没有合适候选再查 market/SkillHub skill |
| 给出本地 Skill zip | 先调用 agent skill create --zip，拿到返回的 skill-... ID 和版本后再创建 Agent |
| 未指定工具 | 使用 CLI 注入的完整默认工具集；显式传 --tool 时全量替换默认工具 |
| 未明确要求多模态工具 | 不查询工具模型，不添加多模态工具集、image_generate/video_generate 或其 Models；保留普通默认工具，不能因所选模型支持多模态输入而自行添加 |
| 未指定环境 | 创建 Session 时自动选择当前项目最新环境；没有可用环境才提示创建或传入环境 ID |
| 创建成功 | 必须回读 agent agent get <agent-id> --format json，展示服务端最终的 Model、System、Tools、Skills、McpServers 和扩展配置 |
| 用户期待 Agent 回复 | 短请求使用 +new session ... --message 或 events send ... --stream；大 payload / 长耗时任务使用 events send --poll，或 send 立即返回后按 cursor 轮询 events / 使用 +tail，不要让所有任务都阻塞等待 |
业务目标澄清
模型、Agent、Skill、MCP provider 等目标无法唯一确定时，遵循
arkcli-shared 的 0/1/N 结构化选择契约：先做一次最小
只读查询，选项只取本轮完整结构化结果中的真实 ID 和区分字段。多个候选会改变远端结果
时使用宿主结构化选择能力；唯一候选直接继续。选择目标只完成消歧，不等于授权后续创建、
更新或删除。
创建任务的主模型选型例外：默认由 AI 按本轮 --query 详情、实时资格与用户意图
择优，复述真实 items[].model 和依据；不能只因有多个候选就停下来问，也不能把排序第一
当作证据或把择优说成“只有一个模型可用”。用户明确的硬指标须用对应版本 metadata
验证；不能自动换身份、计费路径、超出预算或替换用户明确给出的模型。
只有多个候选的能力、版本或费用会实质影响结果且无法从用户意图安全判断时，才进入
模型选择停点：展示真实候选，用户选定前不得查询 Agent Skill，也不得执行 preview、
agent agent create/update、+new-agent、+iterate 或准备后续参数。此时选项是当前
回合的最终输出，之后不再探测写命令 --help 或调用其他工具。择优不替代执行授权，
也不适用于复制、更新、删除时对已有 Agent 的目标消歧。
What ships with it
11 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.
- references/agent.md 36 KB
- references/debug-export.md 2.1 KB
- references/evals.md 13 KB
- references/events-chat.md 19 KB
- references/interfaces-gaps.md 7.5 KB
- references/mcp-vault.md 5.7 KB
- references/model-config.md 4.2 KB
- references/self-hosted.md 4.0 KB
- references/session-files.md 10 KB
- references/session-upgrade.md 6.5 KB
- references/skills.md 11 KB
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.
- 17d ago Changed · +7 lines a1f5e632b305
- 29d ago Changed · +5 lines 0708900dc60d
- 1mo ago Changed · +20 lines f24e54ca0fab
- 1mo ago Changed · +16 lines 407a78df6329
- 1mo ago First seen · 138 lines · 55 tokens per session scan A b82b464bd5ca
arkcli-agent is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 55 tokens to every session and 5,791 once invoked, about $0.0002 per session on Opus 5.5. 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
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
batch-file-ops
Batch-Dateioperationen (Löschen, Verschieben, Kopieren, Auflisten) mit Glob-Mustern. CLI-Werkzeug für effiziente Dateisystem-Operationen. Ohne Abhängigkeiten.
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…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…