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 yunsii/wezdeck --skill session-bridgegit clone --depth 1 https://github.com/yunsii/wezdeckWrote 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/yunsii/wezdeck/session-bridge)<a href="https://agentmods.dev/skills/yunsii/wezdeck/session-bridge"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/session-bridge/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/yunsii/wezdeck/session-bridge"><img src="https://agentmods.dev/badge/skills/yunsii/wezdeck/session-bridge.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 | $0.01035 |
| Opus 5.5 | $0.00030 | $0.00414 |
| Sonnet 5.5 | $0.00015 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
session-bridge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Adapter Kit（Dex · Main）
入口脚本（仓内）：
REPO="${WEZDECK_REPO:-$HOME/github/wezterm-config}"
SB="$REPO/openclaw/scripts/session-bridge.sh"
规范：openclaw/docs/session-bridge.md
tmux 版本策略：docs/tmux-install.md
何时用
| 用户意图 | 命令 |
|---|---|
| 本机 Claude/Codex 卡在哪 | $SB host-status → 必要时 host-capture --target … |
| 飞书侧让 agent 跑一轮 | $SB poke --id dex -m '…'（先 --dry-run 若不确定） |
| 临时点 Continue / 发短文本进 TUI | lease mint → host-send-keys …（先 dry-run） |
| 权限框点 Yes | host-capture 确认 → host-send-keys --approve-visible |
| 查 Dex 会话 | $SB claw-ls / claw-show --id dex |
| 机器人通知 | $SB bot-send --to dex -m '…'（默认 dry-run） |
| 本人飞书说话 | $SB say-as-me --to dex -m '…'（P3；默认 dry-run） |
| 饭点接管聚焦 pane | 快捷键 Ctrl+K w；或 $SB take --focus --confirm-notify。默认 只在 need_human 时 bot→主人（owner），不拿本人身份刷 Dex |
| 查/停盯梢 | $SB watch-status / watch-stop --all |
| 紧急停写 | $SB panic on |
take 只做轻量轮询 + 状态机；不代按 TUI、不每 tick 跑模型。
通知按事件分流（notify_by_event）：need_human→owner（bot DM 主人，汇总后让你决策）；turn_idle / take / ended 默认 none。旧 notify_identity=user+poke 毯子覆盖已不推荐。
TTL 默认 90m，状态跃迁滑动续期（ttl_renew_on_activity）；真闲置满窗才结束。
文案经 NotifyCard（notify_card.py）：优先 attention 结构化字段 + pane kind 抽取，不是 LLM / 整屏 tmux dump。需 feishu_targets.dex_user_id 才能 owner DM。
仅 agent pane：以 pane 前台进程为准；不用标题。扩展新 TUI：在 notify_card.py 的 KIND_EXTRACTORS / KIND_FAMILY 注册解析器即可。
硬规则
- 身份三分：
agent-poke≠bot≠user（say-as-me）；汇报里写清。 - 读宽写窄： 写路径 panic 全拒（exit 75）。
- host-send-keys 需要：有效 lease +
host_allowlist+ 无 panic；禁 C-c/C-z/C-d。 - 遥控 ≠ 写码权（单写者仍成立）。
- tmux client 必须与 server 匹配（脚本自动 probe；勿硬编
/usr/bin/tmux3.4）。 - 密钥/token 不要从 capture 贴回飞书。
配置（仓外）
~/.openclaw/session-bridge.json：
aliases.dex→ session keyhost_allowlist.send_keys_panes→ session 名 glob（如wezterm_*）feishu_targets.dex_user_id/*_chat_id→ bot-send / say-as-medefaults.tmux_bin/receipt/defaults.watch（ttl/interval/notify_to）
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.
- 1mo ago Changed · +2 lines 6a3add5aeb48
- 1mo ago Changed a9aec8454fa5
- 1mo ago First seen · 64 lines · 74 tokens per session scan A 128af752d8bf
session-bridge is a skill published in the GitHub repository yunsii/wezdeck (4 stars, last pushed 5d ago), licensed MIT. It adds 74 tokens to every session and 1,035 once invoked, about $0.0003 per session on Opus 5.5. 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
workflow
Create, run, monitor, cancel, or resume deterministic JavaScript workflows that orchestrate multiple Codex, Claude, Cursor, or Kimi agents. Use for parallel investigation or review, staged agent pipelines, resumable long-running work, or when the user explicitly asks for a workflow, orchestration, fan-out, or several…
orchestrate
Use only when the user explicitly types /orchestrate:orchestrate to decompose a large task, spawn a tree of parallel worker/subplanner/verifier subagents, and collect structured handoffs. Do not invoke autonomously.
sessions
Agent Sessions window architecture — covers the sessions-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agent Sessions window.
launch
Launch and automate VS Code (Code OSS) using agent-browser via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test UI features, or take screenshots of VS Code. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch…
accessibility
Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
component-fixtures
Use when creating or updating component fixtures for screenshot testing, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, and common pitfalls.