Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/ziwang-physics/agentchat/agentchat-oneweb)<a href="https://agentmods.dev/skills/ziwang-physics/agentchat/agentchat-oneweb"><img src="https://agentmods.dev/badge/skills/ziwang-physics/agentchat/agentchat-oneweb.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 5.1 | $0.00129 | $0.07603 |
| Opus 5 | $0.00064 | $0.03802 |
| Sonnet 5 | $0.00026 | $0.01521 |
| Haiku 4.5 | $0.00013 | $0.00760 |
Grade C, and why
AgentChat-OneWeb scanned grade C with 2 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 6d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://127.0.0.1:9222/json/version | python3 -c "import json,sys; print(json.load(sys.stdin).get('Browser','FAIL'))" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:9222/json/version | python3 -c "import json,sys; print(json.load(sys.stdin).get('Browser','FAIL'))" How it starts
The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Fallback Chain — Multi-Provider CDP Bridge
最后更新: 2026-08-09 核心功能: 按优先级链自动降级,确保始终有一个可用的大模型 变更日志: 见 CHANGELOG.md
⚠️ 强制规则 — 调用即执行(首要动作契约)
本 skill 被调用(如 /AgentChat-OneWeb <问题>)时,必须执行 node 命令把用户问题发送到 web AI。禁止只解释用法而不执行,禁止用模型自身知识替代 web AI 的回答。
1. 首要动作契约
读完本 SKILL.md 之后的下一个工具调用必须是:
node ~/.claude/skills/AgentChat-OneWeb/index.js "<用户prompt>"
中间不允许插入文件浏览、架构分析、"我将会…"式的规划叙述(至多一行说明即将执行的命令)。web AI 返回结果后,才可补充你自己的分析。
2. 执行回执(receipt)— 是否执行以此为准,不以叙述为准
每次真实执行(含失败)都会在 stderr 输出一行机器生成的回执:
[receipt] AGENTCHAT_RUN {"run_id":"ac-xxxxxxxxxxxx","skill":"AgentChat-OneWeb","exit":0,"provider_used":"Gemini",...}
- 最终回答末尾必须原样引用这行 receipt(至少包含 run_id、provider_used、exit)。
- 没有 receipt = 没有执行 = 违规,必须回去执行。
run_id为随机生成并同步落盘到~/.claude/skills/AgentChat-OneWeb/data/receipts.jsonl,用户可用grep <run_id>核对——凭空编造无法通过核对。- 执行失败(exit≠0)同样有 receipt:必须引用失败回执并说明原因(限流/未登录/超时…),在此之后才允许用模型自身能力回答,且必须明确标注"web AI 未参与本次回答"。
3. 违规模式(全部禁止)
- ❌ 读完 SKILL.md 后描述 fallback 链、罗列 CLI 参数、讲解架构——却不跑
node index.js - ❌ 以"问题太简单/我已经知道答案"为由跳过执行,直接用模型知识回答
- ❌ 回答中没有
[receipt] AGENTCHAT_RUN行却声称"已通过 web AI 处理"
4. 例外
仅限:--smoke、--doctor,或用户明确要求"只检查环境不发送"。这两种模式不产生 receipt,属预期行为。
5. 本地上下文
网页 AI 无法访问本地文件系统。涉及本地文件/代码/图片时,Claude Code 须先将内容读入 prompt 再发送,禁止只传文件路径。
📐 输出排版规范 — 最终回答强制格式
约束对象是 Claude Code 撰写的最终落地文本;worker 原始输出、代码块、diff、表格与 receipt 行不受约束。
- 结论先行:开头第一段为 ≤50 字的核心结论(TL;DR),直接回答用户根本诉求,无客套话、无方法论铺垫。
- 标题层级:主模块用
##,子观点用###,禁止一级标题#。维度按逻辑聚类为 3–5 块(如:背景/现状/分析/结论),禁止按检索顺序写流水账。 - 视觉焦点:数据、时间、专有名词、核心论点用
**加粗**标出;加粗仅用于焦点引导,每个自然段不超过 2 处。 - 列表纪律:只允许单层无序列表
*,禁止任何多级嵌套列表(保证终端/聊天框阅读体验)。 - 文本密度:叙述性自然段 ≤3 句,新逻辑分支必须换行分段;禁止"总而言之""基于以上搜索结果""作为一个人工智能"等无实质信息的过渡句。
- 信息隔离:引用 web AI 原文片段或外部链接时必须放入
>引用块并标注来源 provider,与自己的分析严格区分。 - 豁免条款(优先级高于第 1–6 条):
[receipt] AGENTCHAT_RUN {...}行(或各步 run_id 清单)必须原样保留在回答末尾的代码块中,禁止改写、加粗、省略——受强制规则 §2 约束。- 降级/失败披露(如"N 个角色降级""web AI 未参与本次回答")属流程透明性要求,不算冗余过渡句,不得删除。
- 代码块、diff、表格不受段落长度与列表层级限制。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 482 lines · 129 tokens per session scan C a1227403b11f
AgentChat-OneWeb is a skill published in the GitHub repository ziwang-Physics/AgentChat (760 stars, last pushed 25d ago), licensed MIT. It adds 129 tokens to every session and 7,603 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…