Borrowing it
Nothing to install: this file belongs to JimmyLv/bibigpt-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JimmyLv/bibigpt-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/JimmyLv/bibigpt-skillWrote 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/instructions/jimmylv/bibigpt-skill/claude-md)<a href="https://agentmods.dev/instructions/jimmylv/bibigpt-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/jimmylv/bibigpt-skill/claude-md/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/instructions/jimmylv/bibigpt-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/jimmylv/bibigpt-skill/claude-md.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 | $0.00751 | $0.00751 |
| Opus 5.5 | $0.00300 | $0.00300 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
bibigpt-skill CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `references/api.md` — REST/OpenAPI 端点 + curl 示例 What it actually says
bibigpt-skill (External Agent Contract)
Audience
这个 package 的内容会被外部 Agent(Claude / Cursor / OpenClaw / Cline / 通义灵码 等)当 skill 加载,是 BibiGPT 对外的契约文档。不是 BibiGPT 团队内部的状态板。
Hard No
写入 skills/**/*.md / references/*.md 时,禁止包含:
- 我们 BibiGPT 的内部 ID(支付宝 APPID、service_id、seller_id、合约号、user_id 等)
- 部署状态、灰度阶段、smoke test 结果、上线时间表
- 服务端 env var 名(
ALIPAY_*/BIBI_*之类) - 内部 commit 号、PR 链接、issue 编号
- 团队内部决策记录("待 X 后切换"等)
Why:agent 不关心我们什么时候上线、是不是已经联调通过;agent 关心它怎么调、收到啥怎么处理、错了怎么 retry。把内部状态塞进去 = 给竞品/逆向人员送情报,也污染了 agent 的上下文。
这些信息归宿:根仓 notes/(团队工作沉淀)+ Claude memory(跨会话状态)。
Hard Yes
写入应当:
- 描述 agent 的行为契约:endpoint、参数、出参 shape、错误码、retry 策略
- 提供 agent 给用户的提示话术模板(如 402 提示)
- 给出 触发意图(什么样的用户问题该调这个工具)
- 写通用价位区间("≤ ¥5 / call"),不写具体数字(容易过期)
同步规则
新增 / 修改 BibiGPT 的 OpenAPI / MCP / CLI 能力,必须同步对应 skill:
- 总结 / 转写 / 章节 →
skills/bibi/ - 已保存视频、笔记、合集 →
skills/bibi-library/ - 订阅频道 / 动态 →
skills/bibi-feed/ - 画面 / 脑图 →
skills/bibi-vision/
不要把 library / feed / vision 再写回 bibi 当全能入口。流程:
- 改
bibigpt-core的能力代码 - 改这个 submodule 里的对应文档(commit + push 子模块)
- 在父仓 bump submodule pointer(commit + push 父仓)
子模块没 push 时父仓 push 会被 husky pre-push 拦下(check-submodule-pushed.sh),别试 --no-verify 绕。
三个相关 reference 的边界
references/cli.md—bibiCLI 命令列表 + flagsreferences/api.md— REST/OpenAPI 端点 + curl 示例references/installation.md— 装 desktop / skill / 配 token / MCPreferences/billing-aipay.md— 402 协议 agent 侧处理(不写我们的 APPID)references/supported-platforms.md— 支持的 URL 类型
更细的内部实现细节、协议字段二进制 layout、错误码完整集等等,放到根仓 notes/,不要塞进 references。
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 · +7 lines · +73 tokens per session cae851893f93
- 2mo ago First seen · 49 lines · 678 tokens per session scan A 2b71bde3acf4
bibigpt-skill CLAUDE.md is an instructions file published in the GitHub repository JimmyLv/bibigpt-skill (138 stars, last pushed 4d ago), licensed MIT. It adds 751 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
bibigpt-skill CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bibigpt-skill CLAUDE.mdJimmyLv/bibigpt-skill | Instructions file | 138 | 4d ago | MIT | A | 751 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |