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 ziwang-Physics/AgentChat --skill agentchat-websubagentgit clone --depth 1 https://github.com/ziwang-Physics/AgentChatWrote 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-websubagent)<a href="https://agentmods.dev/skills/ziwang-physics/agentchat/agentchat-websubagent"><img src="https://agentmods.dev/badge/skills/ziwang-physics/agentchat/agentchat-websubagent.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.02938 |
| Opus 5 | $0.00069 | $0.01469 |
| Sonnet 5 | $0.00028 | $0.00588 |
| Haiku 4.5 | $0.00014 | $0.00294 |
Grade A, and why
AgentChat-WebSubAgent 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 8d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentChat-WebSubAgent
核心原则: Claude Code 大脑 → Kimi 搜索 → (复杂? Gemini 推理) → Claude 合成 → ChatGPT 审查 → Claude 修复 Provider 层:
AgentChat-OneWeb,零代码重复 安全策略: 永不关闭用户 Chrome
⚠️ 强制规则 — 调用即执行
本 skill 被调用时,必须依次执行 Step 1→6。Step 2 和 Step 5 无条件执行,Step 3 由复杂度决定。禁止跳过任何步骤,禁止只解释流程而不执行。
核心约束:
- ❌ 禁止:读了 SKILL.md 后描述流水线、解释角色分工、分析架构——却不跑
node index.js - ❌ 禁止:以"任务太简单/纯本地/不需要搜索"为由跳过 Step 2 (
--search) - ❌ 禁止:以"产出很简单/不需要审查"为由跳过 Step 5 (
--review) - ❌ 禁止:用本地文件读取、代码分析、或 Claude 自身知识替代
node index.js调用 - ❌ 禁止:把本地文件路径写入 prompt 指望网页 AI 自读(它无权访问本地磁盘)。须由 Claude Code 读入内容后再发送
- ✅ 必须:Step 2 和 Step 5 无条件执行。复杂度判定仅影响 Step 3(Gemini 推理)是否跳过
- ✅ 必须:每步产生可验证的
node index.jsJSON 输出,结果返回后才可补充你的解读
执行回执(receipt)— 是否执行以此为准,不以叙述为准
每次 node index.js --search/--reason/--review 的输出 JSON 中都包含机器生成的 receipt 字段
(同时 stderr 打印一行 [receipt] AGENTCHAT_RUN {...}):
"receipt": { "run_id": "ac-xxxxxxxxxxxx", "skill": "AgentChat-WebSubAgent", "mode": "search", "exit": 0, "provider_used": "kimi", ... }
- 最终报告必须逐步列出每次执行的
receipt.run_id(Step 2 一个;Step 3 如执行一个;Step 5 一个)。 - 缺少某一步的 run_id = 该步没有执行 = 违规,必须补跑。
- run_id 随机生成并落盘
skills/AgentChat-WebSubAgent/data/receipts.jsonl,用户可grep <run_id>核对,凭空编造无法通过核对。 - 失败执行(exit≠0)同样有 receipt:引用失败回执、说明降级/失败原因后,才允许以模型自身能力继续该步,并明确标注"web AI 未参与该步"。
反绕过原则: 如果某个步骤"看起来不需要 web AI",正确的做法是仍然通过 node index.js 把本地发现发给 web AI 做验证/补充/交叉检查——而不是跳过该步骤。Step 2 的搜索 prompt 和 Step 5 的审查内容必须包含 Claude 已做的本地分析结果,让 web AI 做二次确认。
自检清单 (Claude Code 在最终输出前必须确认全部完成):
- Step 2:
node index.js --search已执行,返回了 JSON?receipt.run_id = ______ - Step 3: (复杂时)
node index.js --reason已执行?receipt.run_id = ______ (简单时) 已明确记录跳过理由? - Step 5:
node index.js --review已执行,返回了 JSON?receipt.run_id = ______ - Step 6: 审查意见已逐条处理?
- 最终报告已列出以上全部 run_id?
例外: --smoke、--doctor,或用户明确要求"只检查环境不发送"
架构
用户需求 → [1.Claude 规划] → [2.Kimi 搜索] →{复杂?}→ [3.Gemini 推理] → [4.Claude 合成] → [5.ChatGPT 审查] → [6.Claude 修复] → 最终产出
└── 简单: 跳过 ──┘
What ships with it
1 file 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.
- 8d ago First seen · 180 lines · 138 tokens per session scan A 7fc8de57d681
AgentChat-WebSubAgent is a skill published in the GitHub repository ziwang-Physics/AgentChat (761 stars, last pushed 28d ago), licensed MIT. It adds 138 tokens to every session and 2,938 once invoked, about $0.0007 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.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…