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/deepgram/wsh/multi-sessionnpx skills add deepgram/wsh --skill multi-sessiongit clone --depth 1 https://github.com/deepgram/wshWhat 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 | $0.02242 |
| Opus 5 | $0.00026 | $0.01121 |
| Sonnet 5 | $0.00011 | $0.00448 |
| Haiku 4.5 | $0.00005 | $0.00224 |
Grade A, and why
multi-session 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 2d 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.
> 2. **If you do NOT have `wsh_*` tools**: you are in HTTP/curl fallback mode. How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMPORTANT: EXECUTION CONTEXT This skill describes what to do — domain patterns and decision-making. It does NOT describe how to call the API.
- If you have
wsh_*tools (check your toolkit forwsh_send_input,wsh_get_screen, etc.): use them directly. Operation names in this skill generally map to tool names (e.g., "send input" →wsh_send_input). When in doubt, list your availablewsh_*tools.- If you do NOT have
wsh_*tools: you are in HTTP/curl fallback mode. DO NOT GUESS endpoints or CLI subcommands. Load the full API reference first: search your workspace forskills/core/and readSKILL.md. It contains every endpoint with working curl examples and a bootstrap sequence.- Quick bootstrap:
curl -sf --unix-socket ${XDG_RUNTIME_DIR:-/tmp}/wsh/default.http.sock http://localhost/health— if that fails:wsh server -L agent-$$ --ephemeral &and retry.
wsh:multi-session — Parallel Terminal Sessions
Sometimes one terminal isn't enough. You need to run a build while tailing logs. Run tests across three environments simultaneously. Drive multiple processes that each need independent input and output. Multi-session gives you this.
When to Use Multiple Sessions
Use multi-session when:
- Tasks are independent and can run in parallel
- You need isolated environments (different directories, different env vars, different shells)
- A long-running process needs monitoring while you work in another session
- You're coordinating multiple tools that each need their own terminal
Don't use multi-session when:
- A single shell with
&&or&would suffice - The tasks are strictly sequential
- You only need to run one thing at a time
Prerequisites
wsh always runs as a server daemon, so multi-session is
always available. The sessions API endpoint is at
/sessions/. You create sessions explicitly and interact
with each via /sessions/:name/ prefix.
If you're in an attached wsh session (started with wsh),
there's already a default session. You can create
additional sessions via the API alongside it.
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.
- 2d ago First seen · 277 lines · 53 tokens per session scan A a882d3201136
multi-session is a skill published in the GitHub repository deepgram/wsh (5 stars, last pushed 3mo ago), licensed ISC. It adds 53 tokens to every session and 2,242 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.