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 chuancyzhang/deepseek-cowork --skill interactiongit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote 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/chuancyzhang/deepseek-cowork/interaction)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/interaction"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/interaction/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/chuancyzhang/deepseek-cowork/interaction"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/interaction.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.00847 |
| Opus 5.5 | $0.00004 | $0.00339 |
| Sonnet 5.5 | $0.00002 | $0.00169 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
interaction 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interaction Skill
This core built-in Skill is exposed directly when allowed by the current run context. It provides user interaction plus channel-aware artifact delivery.
Tools
request_user_approval
Ask the user to approve or reject a potentially important action.
- message (string, required): The message to display to the user.
- title (string, optional): dialog title.
- severity (string, optional): risk level hint (
low/medium/high). - timeout_seconds (number, optional): timeout before the request is cancelled.
- details (string, optional): extra context for the approval dialog.
request_user_input
Ask the user for text, a single choice, or multiple choices.
- message (string, required): The message to display to the user.
- title (string, optional): dialog title.
- input_mode (string, optional):
text,choice, ormulti_choice. - purpose (string, optional): runtime intent marker;
grill_checkpointis reserved for the grilling summary decision. - options (array, optional): list of selectable options.
- allow_free_text (boolean, optional): allow arbitrary free-text input.
- timeout_seconds (number, optional): timeout before the request is cancelled.
For task clarification, use questionnaire questions with mutually exclusive choices and put the recommended choice first. The runtime removes any caller-supplied custom choice and appends exactly one 自定义 option automatically; callers must not add it themselves.
Questionnaires issued while the runtime is in grilling mode never auto-select a recommended answer on timeout.
publish_artifacts
Publish generated artifacts only when the current messaging channel advertises artifact delivery. Use this tool when:
- A Feishu task needs local files, images, or links delivered in that conversation.
- A DingTalk or WeCom task needs an accessible URL delivered in that conversation.
Channel contract:
- Feishu: native local file/image upload and URL delivery.
- DingTalk / WeCom: URL-only delivery; local-only paths are reported as not delivered.
- QQ / WeChat: this Tool is not exposed.
- Desktop: this Tool is not exposed; report the real local path or URL in the final reply.
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.
- 1mo ago First seen · 72 lines · 9 tokens per session scan A 1705df1edbbc
interaction is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 9 tokens to every session and 847 once invoked, about $0.0000 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…