agentmods.dev

clawbox-chat-stream

A project guide for the ClawBox chat flow, covering its React interface and Bun bridge to OpenClaw. It explains how messages, live updates, tool calls, session history, and titles move through the app.

In plain words
What is it for?
Use it when changing or debugging message streaming, server-sent events, tool-call display, session loading, unread counts, or chat-title generation.
Why use it?
It helps track bugs that cross the frontend and backend instead of treating each layer separately. It also highlights the need to reconcile live events with saved conversation history.

Skill for Claude CodeCodex

22 4mo ago A scan 45 tokens original MIT
View the source file CommonstackAI/ClawBox
Install

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.

agentmods
npx agentmods add skills/commonstackai/clawbox/clawbox-chat-stream
Any agent
npx skills add CommonstackAI/ClawBox --skill clawbox-chat-stream
Clone the repo
git clone --depth 1 https://github.com/CommonstackAI/ClawBox

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00362
Opus 5 $0.00023 $0.00181
Sonnet 5 $0.00009 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured 3d ago against content hash d452d73adc3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawbox-chat-stream 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 3d 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.

.agents/skills/clawbox-chat-stream/SKILL.md · 38 lines

What it actually says

ClawBox Chat Stream

Use this skill when the task involves ClawBox chat flow, assistant streaming, tool event rendering, session history hydration, or title generation.

Read first

  • src/hooks/useChat.ts
  • src/services/ai.ts
  • src/store/chat.ts
  • src/components/chat/
  • internal/routes/chat.ts
  • internal/providers/openclaw-rpc.ts
  • src/services/api.ts

Workflow

  1. Map the end-to-end path: UI event -> frontend store/hook -> SSE parser -> backend route -> OpenClaw RPC event.
  2. If request or response payloads change, update every consumer in the same task instead of leaving cross-layer drift.
  3. For tool-call regressions, verify both streamed events and history rehydration. ClawBox uses live events plus follow-up history reconciliation.
  4. For title or unread-count issues, inspect the finally path in src/hooks/useChat.ts and the corresponding Zustand store updates.

Verification

  • Run npm run build:frontend.
  • Run npm run build:backend.
  • If the local gateway is available, use bun test/openclaw-stream.ts --prompt "..." as a manual smoke test.

Guardrails

  • Never guess OpenClaw protocol fields or event names.
  • Preserve the SSE event types expected by src/services/ai.ts.
  • Keep message block ordering consistent with the text, reasoning, and tool_call model.
Changes

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.

  1. 3d ago First seen · 38 lines · 45 tokens per session scan A d452d73adc3a

Subscribe to this mod's changes

clawbox-chat-stream is a skill published in the GitHub repository CommonstackAI/ClawBox (22 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 362 once invoked, about $0.0002 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 2026-08-30.

Backend and APIsFrontendReactagent-skillsaiassistantopenclaw
Related

Other skills, from other repositories

frontend-conventions

Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.

iflytek/skillhub · 36 tokens

nextjs-expert

Next.js expert for App Router, SSR/SSG, API routes, middleware, and deployment.

RightNow-AI/openfang · 24 tokens

react-expert

React expert for hooks, state management, Server Components, and performance optimization.

RightNow-AI/openfang · 18 tokens

gmail-email

Send emails via Gmail SMTP using App Password authentication.

open-gitagent/gitagent · 13 tokens

example-skill

Example skill that demonstrates the gitagent skills system. Use this to test skill loading and script execution.

open-gitagent/gitagent · 24 tokens

yida-canvas-custom-page

宜搭自定义页面开发规范，使用 YidaCodeCanvas 组件实现现代 React18 自定义页面。用于官网、看板、工作台、列表、详情、门户壳、可视化、hooks 交互，以及需要门户组件、数据管理视图、成员、部门或上传组件的场景。.

openyida/openyida · 77 tokens