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-chatgit 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-chat)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-chat"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-chat/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-chat"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-chat.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 | $0.04140 |
| Opus 5.5 | $0.00047 | $0.01656 |
| Sonnet 5.5 | $0.00024 | $0.00828 |
| Haiku 4.5 | $0.00012 | $0.00414 |
Grade A, and why
arkcli-chat 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli +chat
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
CRITICAL — +chat 在执行之前，务必先用 Read 工具读取 references/arkcli-chat.md，禁止直接盲目调用命令。
CRITICAL — 一次用户要求的回答只发起一次真实 +chat。首次响应不完整、strict JSON 无效或不符合内容要求时，保留并报告该次失败，不自动重试或用第二次响应替换；本地提取、保存、校验失败也只能修复本地交付。只有用户明确要求新一轮或重新生成时才再次调用。
核心概念
--model缺省时 CLI 自动 fallback 到 active profile 的resources.text.default；用户显式传入不同值时按../arkcli-shared/references/profile-defaults.md做漂移提示。+chat是数据面 Responses API（POST /responses）的高层封装：一次请求即返回助手文本。- 支持多模态：用
--input @photo.jpg把本地文件随请求上传，模型可看图/看视频/听音频后回答。图片(.jpg/.png/.webp/...)、视频(.mp4/.mov/...)、音频(.mp3/.wav/.m4a/...)、通用文件按扩展名自动分流。 - 支持流式：
--stream模式逐段输出，先输出推理（thinking），再输出正式回答（response）。 - 支持进度提示：非流式调用在 5s 后开始向 stderr 输出
arkcli +chat: still running… elapsed Xs心跳行（每 10s 一次），避免长调用看不到任何输出；脚本场景可用--no-progress关闭。stdout 不受影响。 - 支持system instructions：
--instructions "..."注入系统级指令。 - 支持采样调节：
--temperature/--top-p/--max-output-tokens。 - 支持思考强度：
--reasoning-effort minimal|low|medium|high（仅在支持 reasoning 的模型上生效）。 - 支持多轮接续：
--store持久化本次响应，下一次用--previous-response-id <id>接续。 - 支持Tools：
--tools web_search（简单语法糖）或--tools-file tools.json（function 等完整形态），配合--tool-choice auto|required|none与--max-tool-calls。详见references/tools.md。 - 支持对账面命令：
arkcli chat get/delete/list-input-items <response-id>，对--store过的 response 做 CRUD，详见references/chat-meta.md。 - 支持缓存与思考：
--caching enabled|disabled（配--cache-prefix）控制服务端 prompt cache；--thinking auto|enabled|disabled控制思考阶段；--expire-at <epoch_sec>给 stored response 加过期。详见references/caching-thinking.md。 - 支持流式事件：
--stream --include-events输出原始 SDK 事件 NDJSON（每行一个 JSON），供 autotest / agent 程序化消费。详见references/stream-events.md。 - 支持可验证的严格 JSON：
--text-format json_schema --text-schema <file> --text-strict不只把约束传给服务端，还会在客户端确认响应完整、是直接 JSON 且符合 Schema；否则非零退出。严格流式会先缓冲，校验成功后才输出，避免泄出半截 JSON。详见references/text-format.md。 - 输出 schema（务必先看）：
+chat返回是 arkcli 扁平 schema（{id, model, content, reasoning_content, usage, ...}），不是 Responses API 原生output[].content[].text嵌套；助手文本直接用.content取。--format不会切换 shape。详见references/arkcli-chat.md的「返回值」段。 - 用户临时提供
--api-key/--base-url/ Endpoint 时，MUST 读取../arkcli-shared/references/execution-context.md。不要从 Key 文本猜套餐类型，也不要把临时值写入 profile。 --dry-run只在本地构造preview.v1请求摘要与无 secret 的执行上下文；不会读取在线元数据、刷新凭证、调用 Responses API、产生 token 用量或存储 response。在线依赖必须列为unresolved。
What ships with it
7 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.
- 17d ago Changed · +4 lines 61a75671265c
- 29d ago Changed · +11 lines 5c5956d62716
- 1mo ago Changed · +11 lines 69857686176a
- 1mo ago Changed · +11 lines · +29 tokens per session 941e844a036f
- 1mo ago First seen · 105 lines · 89 tokens per session scan A 98f8cc5ea2ed
arkcli-chat is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 118 tokens to every session and 4,140 once invoked, about $0.0005 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…