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 agentmods add skills/summersec/sumsec-skills/multi-platform-plugin-guidenpx skills add SummerSec/SumSec-Skills --skill multi-platform-plugin-guidegit clone --depth 1 https://github.com/SummerSec/SumSec-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/summersec/sumsec-skills/multi-platform-plugin-guide)<a href="https://agentmods.dev/skills/summersec/sumsec-skills/multi-platform-plugin-guide"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/multi-platform-plugin-guide.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.05701 |
| Opus 5 | $0.00026 | $0.02851 |
| Sonnet 5 | $0.00011 | $0.01140 |
| Haiku 4.5 | $0.00005 | $0.00570 |
Grade A, and why
multi-platform-plugin-guide 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 4d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
多平台插件开发指南（AI Inner OS）
本仓入口：优先执行文末 SumSec-Skills 发布清单（本仓）。前半部分保留 AI Inner OS 多平台矩阵作为参考；本仓还落地 OpenClaw / OpenCode / Hermes / DeepSeek Harness（DSH）专用入口。
上游矩阵参考：AI Inner OS 主仓根目录 CLAUDE.md。若本技能的通用平台说明与 AI Inner OS 主仓不一致，先更新上游矩阵，再同步本技能。
何时使用
- 修改
hooks/hooks.json、.claude-plugin/、.codex-plugin/、.cursor-plugin/、.agents/plugins/marketplace.json、根plugin.json、openclaw.plugin.json或 release 版本字段。 - 修改根
package.json的dsh.bundle.patch/ DSH keywords、dsh/cordis.patch.yml、dsh/README.md、scripts/validate-dsh.mjs或 profile bundle 安装说明。 - 修改
hooks/、codex/、cursor/下的 hook 适配器，或共享库hooks/lib/。 - 更新必须和 manifest 保持一致的安装文档，例如
cursor/README.md、docs/install-cursor.md、codex/README.md、docs/install-codex.md。 - 准备跨平台 release、插件市场发布、插件缓存更新或多平台能力对齐。
官方文档优先
开发或审查任何平台适配前，先查看对应平台最新官方文档。本技能只记录本仓库当前约定；如果官方规范变化，以官方文档为准，再同步更新仓库实现、CLAUDE.md 和本技能。
| 平台 | 官方开发指南 |
|---|---|
| Claude Code | Plugins reference |
| Codex | Build plugins |
| Cursor | Plugins Reference |
| OpenClaw | Building plugins、Skills |
| OpenCode | Plugins |
| Hermes Agent | Plugins、Skills System |
| DeepSeek Harness | deepseek-ai/deepseek-harness、@deepseek-ai/dsh；本仓当前按 0.1.0-rc.6 验证，该包仍为 prerelease，升级前必须重新检查 package manifest、profile 与 Cordis patch contract。 |
默认流程：
- 读取对应平台最新官方指南。
- 对照本仓库
CLAUDE.md和现有实现。 - 只实现官方已支持的 manifest 字段、hook 事件和路径规则。
- 如果官方规范与仓库文档冲突，先修实现，再同步 README、安装文档、
CLAUDE.md和本技能。
插件注册地图
| Role | Path |
|---|---|
| Claude Code hook 注册 | hooks/hooks.json |
| Claude Code 插件清单 | .claude-plugin/plugin.json |
| Claude marketplace 入口 | .claude-plugin/marketplace.json |
| Codex 插件清单 | .codex-plugin/plugin.json |
| Codex 仓库级 marketplace | .agents/plugins/marketplace.json |
| Cursor 插件清单 | .cursor-plugin/plugin.json |
| Cursor marketplace 入口 | .cursor-plugin/marketplace.json |
| OpenClaw 插件清单 | openclaw.plugin.json |
| OpenClaw 插件入口 | openclaw/index.js |
| OpenCode 插件入口 | opencode/plugins/inner-os.js |
| Hermes Skill | hermes/skills/inner-os/SKILL.md |
| DeepSeek Harness bundle manifest | 根 package.json 的 dsh.bundle.patch |
| DeepSeek Harness bundle patch | dsh/cordis.patch.yml |
| 仓库级元数据 | plugin.json |
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.
- 4d ago First seen · 237 lines · 53 tokens per session scan A c4188eb68753
multi-platform-plugin-guide is a skill published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 19d ago), licensed Apache-2.0. It adds 53 tokens to every session and 5,701 once invoked, about $0.0003 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
dsh-web-pre-push-checks
Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
dsh-sdk-upgrade
Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout — including syncing the project's declared DSH host-version floor…
dsh-web-sdk-compatibility
Adapt and repair dsh-web after an approved official @deepseek-ai SDK/runtime cohort is selected or installed. Compare public API, type, service-injection, module-table, protocol, and behavior changes; map every change to repository consumers; implement the smallest fixes and durable compatibility contracts; handle…
ov-experience-memory
Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools. Use before or during executable, multi-step, or tool-based work such as coding, file or data changes, configuration, deployment, workflow execution, and failure recovery when prior operational…
dsh-doc-site-sync
Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content…