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 ddpie/lark-mcp-on-agentcore --skill lark-appsgit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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/ddpie/lark-mcp-on-agentcore/lark-apps)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-apps"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-apps/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/ddpie/lark-mcp-on-agentcore/lark-apps"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-apps.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 | $0.00223 | $0.03659 |
| Opus 5 | $0.00112 | $0.01829 |
| Sonnet 5 | $0.00045 | $0.00732 |
| Haiku 4.5 | $0.00022 | $0.00366 |
Grade A, and why
lark-apps 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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apps (v1)
妙搭应用属于用户资产（MCP server 自动处理认证、scope、高风险确认、_notice 等通用处理，不要在本 skill 里复制）。妙搭应用有三条开发路径：本地全栈（拉源码本地写）/ HTML 托管（发布静态产物）/ 云端会话（妙搭 AI 生成）。
意图路由
按具体操作查命令（开发路径先用下方「选择开发路径」判定表定好再进来取命令）：
| 用户意图 | 先用 | 按需读取 |
|---|---|---|
| 创建新应用资产、拿 app_id | lark_apps_create |
lark_get_skill(domain="apps", section="create") |
| 找已有 app_id、按名字过滤应用 | lark_apps_list(keyword="<name>") |
lark_get_skill(domain="apps", section="list") |
| 查单个应用详情（类型、名称、发布状态等） | lark_apps_get(app_id="<app_id>") |
lark_get_skill(domain="apps", section="get") |
| 改应用名或描述 | lark_apps_update |
lark_get_skill(domain="apps", section="update") |
发布本地 index.html 或静态目录为可访问 URL |
lark_apps_html_publish |
lark_get_skill(domain="apps", section="html-publish") |
开发已有应用 / 初始化本地仓库（开发方式已定为本地后；先解析 app_id，勿 lark_apps_create 新建） |
lark_apps_init（或手动 lark_apps_git_credential_init + 原生 git）。执行前必读 lark_get_skill(domain="apps", section="local-dev")，含端到端流程和领域规则 |
lark_get_skill(domain="apps", section="init")、lark_get_skill(domain="apps", section="git-credential") |
本地开发时 .env.local 损坏/丢失，重新拉取启动期环境变量 |
lark_apps_env_pull |
lark_get_skill(domain="apps", section="env-pull") |
| 管理应用环境变量（查看/设置/删除） | lark_apps_env_list、lark_apps_env_set、lark_apps_env_delete |
lark_get_skill(domain="apps", section="env") |
| 查线上日志、Trace、请求数、错误率、延迟、CPU、memory、PV/UV/访问量 | lark_apps_log_list、lark_apps_log_get、lark_apps_trace_list、lark_apps_trace_get、lark_apps_metric_list、lark_apps_analytics_list |
lark_get_skill(domain="apps", section="observability") |
| 看表 / 看结构 / 初始化多环境 / 导入导出数据 / 变更追溯 / 行级审计 / dev→online 发布 / 时间点恢复 / 查 DB 用量 | lark_apps_db_table_list、lark_apps_db_table_get、lark_apps_db_env_create、lark_apps_db_data_export / lark_apps_db_data_import、lark_apps_db_changelog_list、lark_apps_db_audit_status / lark_apps_db_audit_enable / lark_apps_db_audit_disable / lark_apps_db_audit_list、lark_apps_db_env_diff / lark_apps_db_env_migrate、lark_apps_db_recovery_diff / lark_apps_db_recovery_apply、lark_apps_db_quota_get |
lark_get_skill(domain="apps", section="db") |
| 逐条执行 SQL（SELECT / DML / DDL） | lark_apps_db_execute |
lark_get_skill(domain="apps", section="db-execute") |
| 管理应用文件存储：上传/下载本地文件、列出/查看/删除已存文件、生成临时分享链接、查存储用量 | lark_apps_file_upload / lark_apps_file_download / lark_apps_file_list / lark_apps_file_get / lark_apps_file_sign / lark_apps_file_delete / lark_apps_file_quota_get |
lark_get_skill(domain="apps", section="file") |
| 部署/上线全栈应用（"部署""上线""推上去并部署""发布到云端"）；查发布状态/历史 | lark_apps_release_create（部署上线动作）、lark_apps_release_get（轮询发布结果，finished 给 online_url / failed 给 error_logs）、lark_apps_release_list |
lark_get_skill(domain="apps", section="release-create")、lark_get_skill(domain="apps", section="release-get")、lark_get_skill(domain="apps", section="release-list") |
| 设置或查看运行时可见范围 | lark_apps_access_scope_set、lark_apps_access_scope_get |
lark_get_skill(domain="apps", section="access-scope-set")、lark_get_skill(domain="apps", section="access-scope-get") |
| 云端 Agent 生成/迭代应用（开发方式已定为云端后） | lark_apps_session_create -> lark_apps_chat -> lark_apps_session_get |
lark_get_skill(domain="apps", section="cloud-dev") |
| 管理妙搭应用开放 API Key（创建/查看/启停/重置/删除凭证；密钥仅 create/reset 一次性返回） | lark_apps_openapi_key_list / lark_apps_openapi_key_get / lark_apps_openapi_key_create / lark_apps_openapi_key_update / lark_apps_openapi_key_enable / lark_apps_openapi_key_disable / lark_apps_openapi_key_delete / lark_apps_openapi_key_reset |
lark_get_skill(domain="apps", section="openapi-key") |
| 查看某次会话某一轮（turn）的回复消息（含仍在生成中的本轮）/ 导出上一轮模型回复（"这一轮回复了什么""上一轮的回复""导出某轮消息"） | 先 lark_apps_session_get（取 latest_turn.turn_id）-> lark_apps_session_messages_list(turn_id="<id>")（仅 user 身份；分页用 page_token） |
lark_get_skill(domain="apps", section="session-messages-list") |
| 外部能力(AI模型能力和飞书平台能力)集成/插件/Plugin/Capability | lark_apps_plugin_install、lark_apps_plugin_list、lark_apps_plugin_uninstall |
lark_get_skill(domain="apps", section="plugin-install")、lark_get_skill(domain="apps", section="plugin-uninstall")、lark_get_skill(domain="apps", section="plugin-list") |
What ships with it
25 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/lark-apps-access-scope-get.md 1004 B
- references/lark-apps-access-scope-set.md 1.9 KB
- references/lark-apps-cloud-dev.md 8.9 KB
- references/lark-apps-create.md 1.5 KB
- references/lark-apps-db-execute.md 3.6 KB
- references/lark-apps-db.md 13 KB
- references/lark-apps-env-pull.md 1.5 KB
- references/lark-apps-env.md 2.6 KB
- references/lark-apps-file.md 5.7 KB
- references/lark-apps-get.md 1.4 KB
- references/lark-apps-git-credential.md 1.8 KB
- references/lark-apps-html-publish.md 3.4 KB
- references/lark-apps-init.md 2.0 KB
- references/lark-apps-list.md 2.0 KB
- references/lark-apps-local-dev.md 6.0 KB
- references/lark-apps-observability.md 3.7 KB
- references/lark-apps-openapi-key.md 4.4 KB
- references/lark-apps-plugin-install.md 1.3 KB
- references/lark-apps-plugin-list.md 666 B
- references/lark-apps-plugin-uninstall.md 638 B
- references/lark-apps-release-create.md 1.9 KB
- references/lark-apps-release-get.md 1.8 KB
- references/lark-apps-release-list.md 1.0 KB
- references/lark-apps-session-messages-list.md 2.9 KB
- references/lark-apps-update.md 975 B
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 · 89 lines · 223 tokens per session scan A e3b4744bde4f
lark-apps is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 11d ago), licensed MIT. It adds 223 tokens to every session and 3,659 once invoked, about $0.0011 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
gemigo-cli
Use when the user wants to publish an already-built static website or front-end app through GemiGo, such as a Vite/React/Vue static build, plain HTML/CSS/JS page, landing page, demo, docs site, or small browser app, and get a hosted public URL.
vercel-deployments
Deploy frontend and full-stack apps on Vercel with previews, edge functions, environment promotion, and production guardrails. Use when shipping Next.js, SvelteKit, or static sites with zero-config CI/CD.
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
prowler-ui
Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn, folder placement, actions/adapters, shared types/hooks/lib).
tailwind-4
Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).
react-19
React 19 patterns with React Compiler. Trigger: When writing React 19 components/hooks in .tsx (React Compiler rules, hook patterns, refs as props). If using Next.js App Router/Server Actions, also use nextjs-16.