What is 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.

Use it when changing or debugging message streaming, server-sent events, tool-call display, session loading, unread counts, or chat-title generation.

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.

clawbox-chat-stream — Skill for Claude Code and Codex by CommonstackAI

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.

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.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/commonstackai/clawbox/clawbox-chat-stream/github.svg)](https://agentmods.dev/skills/commonstackai/clawbox/clawbox-chat-stream)

Your own site

<a href="https://agentmods.dev/skills/commonstackai/clawbox/clawbox-chat-stream"><img src="https://agentmods.dev/badge/skills/commonstackai/clawbox/clawbox-chat-stream/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/commonstackai/clawbox/clawbox-chat-stream"><img src="https://agentmods.dev/badge/skills/commonstackai/clawbox/clawbox-chat-stream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00045	$0.00362
Opus 5.5	$0.00018	$0.00145
Sonnet 5.5	$0.00009	$0.00072
Haiku 4.5	$0.00005	$0.00036

Measured 2mo ago against content hash d452d73adc3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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

Map the end-to-end path: UI event -> frontend store/hook -> SSE parser -> backend route -> OpenClaw RPC event.
If request or response payloads change, update every consumer in the same task instead of leaving cross-layer drift.
For tool-call regressions, verify both streamed events and history rehydration. ClawBox uses live events plus follow-up history reconciliation.
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.

2mo 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 6mo ago), licensed MIT. It adds 45 tokens to every session and 362 once invoked, about $0.0002 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 2026-08-30.

Backend and APIs Frontend React agent-skills ai assistant openclaw

nextjs-pages-router

Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.

trpc/trpc · 67 tokens

middlewares

Create and compose tRPC middleware with t.procedure.use(), extend context via opts.next({ ctx }), build reusable middleware with .concat() and .unstablepipe(), define base procedures like publicProcedure and authedProcedure. Access raw input with getRawInput(). Logging, timing, OTEL tracing patterns.

trpc/trpc · 63 tokens

non-json-content-types

Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).

trpc/trpc · 75 tokens

server-side-calls

Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.

trpc/trpc · 61 tokens

adapter-express

Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.