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 serejaris/kimi-skills --skill kimi-help-centergit clone --depth 1 https://github.com/serejaris/kimi-skillsWrote 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/serejaris/kimi-skills/kimi-help-center)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/kimi-help-center"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/kimi-help-center/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/serejaris/kimi-skills/kimi-help-center"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/kimi-help-center.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 | $0.00189 | $0.01732 |
| Opus 5 | $0.00095 | $0.00866 |
| Sonnet 5 | $0.00038 | $0.00346 |
| Haiku 4.5 | $0.00019 | $0.00173 |
Grade A, and why
kimi-help-center scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -fsSL https://cdn.kimi.com/kimi-claw/uninstall.sh) 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.
Kimi Tutorial & Help
Usage
When user questions involve Kimi subscription/membership services, user guides, membership benefits, or Agent features (e.g. Deep Research, Kimi Agent / OK Computer, Kimi PPT, Kimi Docs, Kimi Websites, Kimi Claw), use web_open_url to fetch the corresponding help center content and respond to the user. Include images in your response when available.
Help center version is determined by account type, not language:
- Mainland China (+86 phone) →
https://www.kimi.com/zh-cn/help/* - Global/Overseas (non-+86, Google account, etc.) →
https://www.kimi.com/help/*
Workflow
- Determine account type: +86 or mentions China → zh-cn; non-+86 / Google / overseas → help. When unclear, default to
zh-cnfor Chinese questions,helpfor English. - Check corrections: Read
references/corrections-memory.mdbefore answering to avoid known mistakes. - Route: Read
references/routing-tables.mdto find the relevant article. - Fetch: Use
web_open_urlto read the article in the appropriate language version. - Answer: Summarize in the user's language. Include the source URL.
- Call out regional differences when relevant (platforms, payments, emails, URLs).
<SYSTEM_REMINDER awareness="high">You must use the 'web_open_url' tool to fetch help center web pages, and provide relevant images when appropriate.</SYSTEM_REMINDER>
Example
User asks: "What is Kimi Claw and how do I install it?"
- Check
references/routing-tables.md→ route tokimi-claw/overview. - Use
web_open_urltool to read the help center content:
{
"urls": ["https://www.kimi.com/help/kimi-claw/overview"]
}
- Summarize the content and respond to the user in a friendly, helpful tone.
Reference Resources
Choose the most relevant document(s) based on the user's question:
| Topic | When to use | File |
|---|---|---|
| Overview | User asks "what is Kimi", product positioning, general feature introduction | references/product-overview.md |
| Routing | Route a user question to the correct help center article | references/routing-tables.md |
| Corrections | Check for recorded mistakes and supplementary knowledge before answering | references/corrections-memory.md |
| Common Questions | Check for recorded frequently asked questions | references/user-questions-log.md |
| Getting Started | User asks about basic usage, chat modes, search, memory | help/getting-started/* |
| Agent Mode | User asks about Agent mode, OK Computer, Agent Swarm | help/agent/* |
| Deep Research | User asks about Deep Research feature and usage | help/deep-research/* |
| PPT / Slides | User asks about Kimi Slides generation | help/slides/* |
| Docs & Sheets | User asks about document and spreadsheet features | help/docs-and-sheets/* |
| Websites | User asks about Kimi Websites | help/websites/* |
| Kimi Claw | User asks about Kimi Claw, deployment, platforms | help/kimi-claw/* |
| Membership | User asks about subscription, pricing, benefits, billing, invoices, usage, rate limits | help/membership/* |
| Kimi Code | User asks about the developer coding assistant, terminal agent, IDE integration, or coding workflow | help/kimi-code/* |
| Kimi API | User asks about the API service | help/kimi-api/* |
| FAQ / Others | Account issues, chat problems, no match above | help/others/* |
What ships with it
3 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.
- 9d ago First seen · 142 lines · 189 tokens per session scan A 452d7852b678
kimi-help-center is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 189 tokens to every session and 1,732 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
explain-this
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "help me understand this", "what does…
understand-change
Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change", "help me understand what changed"…
ape-visualize
Builds interactive, browser-based 3D Three.js visualizations of any mathematics or science concept as a single, self-contained HTML file. Takes a concept and a depth level (Simple, Intermediate, Advanced). Trigger on "ape visualize", "ape visualize math", "ape visualize science", "visualize math", "visualize science"…
ape-quiz-me
Quizzes you on content you claim to have read -- Socratic, one question at a time, hints that narrow but never reveal. Ends with a verdict on what you understood versus merely recited. Trigger on "ape quiz me", "quiz me on this", "test my understanding", "did I actually get this", or any request to be tested on shared…
ape-write-pseudocode
Guidelines for writing pseudocode for functions and algorithms. Use this skill whenever the user asks to write pseudocode, sketch out an algorithm, or describe the logic of a function at a high level. Trigger on phrases like "write pseudocode", "sketch this algorithm", "pseudocode for this function", or "describe the…