Borrowing it
Nothing to install: this file belongs to miuiadmin/hapi-hmos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/miuiadmin/hapi-hmos/main/.claude/skills/hmos-arkts-knowledge-retriever/SKILL.mdgit clone --depth 1 https://github.com/miuiadmin/hapi-hmosWrote 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/miuiadmin/hapi-hmos/hmos-arkts-knowledge-retriever)<a href="https://agentmods.dev/skills/miuiadmin/hapi-hmos/hmos-arkts-knowledge-retriever"><img src="https://agentmods.dev/badge/skills/miuiadmin/hapi-hmos/hmos-arkts-knowledge-retriever/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/miuiadmin/hapi-hmos/hmos-arkts-knowledge-retriever"><img src="https://agentmods.dev/badge/skills/miuiadmin/hapi-hmos/hmos-arkts-knowledge-retriever.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 | $0.00074 | $0.02315 |
| Opus 5 | $0.00037 | $0.01157 |
| Sonnet 5 | $0.00015 | $0.00463 |
| Haiku 4.5 | $0.00007 | $0.00231 |
Grade A, and why
hmos-arkts-knowledge-retriever 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 8d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
60 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.
- README.md 340 B
- references/arkts-language-guide/01-getting-started-with-arkts/arkts-overview.md 2.4 KB
- references/arkts-language-guide/02-basic-syntax/advanced-operators.md 13 KB
- references/arkts-language-guide/02-basic-syntax/classes.md 14 KB
- references/arkts-language-guide/02-basic-syntax/collection-types.md 17 KB
- references/arkts-language-guide/02-basic-syntax/concurrency.md 13 KB
- references/arkts-language-guide/02-basic-syntax/control-flow.md 16 KB
- references/arkts-language-guide/02-basic-syntax/enumerations.md 9.8 KB
- references/arkts-language-guide/02-basic-syntax/error-handling.md 8.8 KB
- references/arkts-language-guide/02-basic-syntax/functions.md 17 KB
- references/arkts-language-guide/02-basic-syntax/generics.md 12 KB
- references/arkts-language-guide/02-basic-syntax/inheritance.md 10 KB
- references/arkts-language-guide/02-basic-syntax/initialization.md 12 KB
- references/arkts-language-guide/02-basic-syntax/interfaces.md 12 KB
- references/arkts-language-guide/02-basic-syntax/methods.md 13 KB
- references/arkts-language-guide/02-basic-syntax/properties.md 12 KB
- references/arkts-language-guide/02-basic-syntax/strings.md 14 KB
- references/arkts-language-guide/02-basic-syntax/type-casting.md 11 KB
- references/arkts-language-guide/03-common-library/arkts-json.md 8.8 KB
- references/arkts-language-guide/03-common-library/arkts-utils-overview.md 768 B
- references/arkts-language-guide/03-common-library/buffer.md 3.2 KB
- references/arkts-language-guide/03-common-library/container-overview.md 914 B
- references/arkts-language-guide/03-common-library/linear-container.md 19 KB
- references/arkts-language-guide/03-common-library/nonlinear-container.md 21 KB
- references/arkts-language-guide/03-common-library/xml-conversion.md 4.2 KB
- references/arkts-language-guide/03-common-library/xml-generation.md 5.6 KB
- references/arkts-language-guide/03-common-library/xml-overview.md 2.0 KB
- references/arkts-language-guide/03-common-library/xml-parsing.md 9.8 KB
- references/arkts-language-guide/04-concurrency/arkts-async-lock-introduction.md 2.9 KB
- references/arkts-language-guide/04-concurrency/arkts-collections-introduction.md 28 KB
- references/arkts-language-guide/04-concurrency/arkts-condition-variable-introduction.md 3.8 KB
- references/arkts-language-guide/04-concurrency/arkts-sendable-module.md 5.4 KB
- references/arkts-language-guide/04-concurrency/arkts-sendable.md 14 KB
- references/arkts-language-guide/04-concurrency/arraybuffer-object.md 5.1 KB
- references/arkts-language-guide/04-concurrency/ason-parsing-generation.md 2.4 KB
- references/arkts-language-guide/04-concurrency/async-concurrency-overview.md 8.7 KB
- references/arkts-language-guide/04-concurrency/batch-database-operations-guide.md 21 KB
- references/arkts-language-guide/04-concurrency/concurrency-faq.md 26 KB
- references/arkts-language-guide/04-concurrency/concurrency-overview.md 2.5 KB
- references/arkts-language-guide/04-concurrency/concurrent-loading-modules-guide.md 6.1 KB
- references/arkts-language-guide/04-concurrency/container-object.md 2.7 KB
- references/arkts-language-guide/04-concurrency/cpu-intensive-task-development.md 8.6 KB
- references/arkts-language-guide/04-concurrency/global-configuration-guide.md 6.5 KB
- references/arkts-language-guide/04-concurrency/independent-time-consuming-task.md 3.9 KB
- references/arkts-language-guide/04-concurrency/interthread-communication-overview.md 2.8 KB
- references/arkts-language-guide/04-concurrency/io-intensive-task-development.md 4.6 KB
- references/arkts-language-guide/04-concurrency/long-time-task-guide.md 3.1 KB
- references/arkts-language-guide/04-concurrency/long-time-task-overview.md 1.5 KB
- references/arkts-language-guide/04-concurrency/makeobserved-sendable.md 3.3 KB
- references/arkts-language-guide/04-concurrency/multi-thread-cancel-task.md 2.5 KB
- references/arkts-language-guide/04-concurrency/multi-thread-concurrency-overview.md 11 KB
- references/arkts-language-guide/04-concurrency/multi-time-consuming-tasks.md 5.0 KB
- references/arkts-language-guide/04-concurrency/multithread-develop-overview.md 1.3 KB
- references/arkts-language-guide/04-concurrency/napi-coerce-to-native-binding-object.md 17 KB
- references/arkts-language-guide/04-concurrency/napi-define-sendable-object.md 9.7 KB
- references/arkts-language-guide/04-concurrency/native-interthread-shared.md 11 KB
- references/arkts-language-guide/04-concurrency/normal-object.md 3.2 KB
- references/arkts-language-guide/04-concurrency/resident-task-guide.md 4.1 KB
- references/arkts-language-guide/04-concurrency/resident-task-overview.md 1.3 KB
- references/arkts-language-guide/04-concurrency/sendable-constraints.md 17 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.
- 8d ago First seen · 310 lines · 74 tokens per session scan A 38ae6aa7669c
hmos-arkts-knowledge-retriever is a skill published in the GitHub repository miuiadmin/hapi-hmos (1 stars, last pushed 29d ago), licensed AGPL-3.0. It adds 74 tokens to every session and 2,315 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 2026-08-31.
Other skills, from other repositories
harmonyos-development
Use when developing, reviewing, debugging, or migrating HarmonyOS NEXT native apps with ArkTS, ArkUI, DevEco Studio, DevEco Code, DevEco CLI, Agent Framework Kit, Stage model, UIAbility, .ets, module.json5, oh-package.json5, HAP/HSP/HAR, API 22-24, API 26 Beta1, HarmonyOS 6.1, HarmonyOS 6.1.1 Release, HarmonyOS 7…
harmonyos-app-dev
A development skill for building HarmonyOS NEXT applications with ArkTS and ArkUI. HarmonyOS NEXT is Huawei’s application platform; ArkTS is its programming language and ArkUI is its interface framework.
warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…
zcode-delegate
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…
claude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…
kimi-delegate
Delegate a coding task to the Kimi Code CLI (kimi) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Kimi - phrasings like "have Kimi implement X", "delegate this to Kimi", "run it through Kimi Code", or "use Kimi to…