Borrowing it
Nothing to install: this file belongs to snake-aabb-wtf/deepseek-web2api-free. 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/snake-aabb-wtf/deepseek-web2api-free/main/AGENTS.mdgit clone --depth 1 https://github.com/snake-aabb-wtf/deepseek-web2api-freeWrote 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/snake-aabb-wtf/deepseek-web2api-free/agents-md)<a href="https://agentmods.dev/instructions/snake-aabb-wtf/deepseek-web2api-free/agents-md"><img src="https://agentmods.dev/badge/instructions/snake-aabb-wtf/deepseek-web2api-free/agents-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/snake-aabb-wtf/deepseek-web2api-free/agents-md"><img src="https://agentmods.dev/badge/instructions/snake-aabb-wtf/deepseek-web2api-free/agents-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 | $0.42157 | $0.42157 |
| Opus 5.5 | $0.16863 | $0.16863 |
| Sonnet 5.5 | $0.08431 | $0.08431 |
| Haiku 4.5 | $0.04216 | $0.04216 |
Grade C, and why
deepseek-web2api-free AGENTS.md scanned grade C with 3 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 9d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST ... -d '{"messages":[{"role":"user","content":"你好"}],"stream":true}' Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- 该文件**必须** `chmod 600`、所在目录 `700`。含明文 DeepSeek token+cookie，泄露=账号被滥用。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8080/health How it starts
The opening of the file, as written. The whole thing — 2,750 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — DeepSeek Chat API Proxy (Preview)
当前发布版本：v4.1.5。中文变更与升级说明见 docs/release-notes/v4.1.5.md。FastAPI、管理接口及 WebUI 包元信息已同步为 4.1.5；下文旧版本记录保留历史版本号。
Responses API（2026-10-27）
-
工具解析兼容
<|DSML|...>与全角竖线<｜DSML｜...>，wrapper 支持tool_calls/tool_call/calls；parameter string="true"保持字符串类型和内容。tool_dsml.tool_block_end提供跳过 CDATA 的原文批次终点，StreamSieve据此等整批闭合再发布，并保留后续正文。不得全局替换命令正文中的字符。复现截图格式的回归见tests/test_dsml_variants.py；真实 CLI 变体验收使用scripts/verify_codex_responses.py --dsml-variant --cli <可执行文件>。 -
Anthropic 非流式正文按是否存在
tool_calls选择cleaned或原始content，不能使用cleaned or content，否则纯工具响应会回填原始标签。tests/test_tool_protocol_routes.py覆盖三个端点的流式/非流式六条路由及纯工具、正文混合工具、普通回答的正文选择。 -
DSML 起始识别与批次闭合共用
[|｜]+分隔符规则；逐字符输入时须保留尚未完整到达的重复竖线前缀，并受现有缓冲上限约束。不能只在完整文本解析器放宽语法，否则 SSE 会先泄漏正文。重复分隔符回归见tests/test_dsml_repeated_separators.py，路由矩阵覆盖三个端点的单/双/混合竖线。 -
/v1/responsesPOST +/{id}GET/DELETE 由responses_routes.py组合注入的运行时依赖，不通过 HTTP 转调聊天补全，不导入 server。 -
chat_service.py/chat_types.py提供协议无关的 prompt、执行结果与事件；chat_runtime.py共用取消安全的线程与账号生命周期。原四条聊天路径复用这些基础能力。 -
responses_format.py管理受支持的 Items、函数 schema 校验和 Response；responses_stream.py管理带序号、稳定 ID/索引的 Responses SSE；response_store.py管理有界、调用方隔离的不可变增量快照。 -
responses_compat.py在请求边界消费有界的 Codex 缓存/客户端元数据及 reasoning/include/verbosity 提示；不进入 prompt、日志或快照，不改变调用方身份、服务端思考策略，也不伪造加密状态。未知功能参数仍严格拒绝。可选真实 CLI 验收见scripts/verify_codex_responses.py，工具范围及限制以 Responses 文档为准。 -
previous_response_id重建所属分支，在原账号/凭证上创建全新会话并重放历史图片引用；不要直接复用可变 SESSION_CACHE，否则会污染分支或继承已替换的 instructions。 -
状态只存内存，祖先删除/过期/回收可能使子链无法续聊；不保存原始图片或凭证。默认限制、SDK 示例和明确不支持的参数见 Responses 文档。
-
第二阶段：
responses_tools.py管理 strict 规范化/有效定义/批次校验；显式 parallel_tool_calls=true 支持最多64次调用，默认false。所有待解决结果按 call_id 关联并须完整提供；完整 DSML 批次在发出函数 Item 之前整体校验。 -
execution_observer.py是通用可选计时回调，responses_observability.py仅投影白名单诊断字段；共享准备链不得导入 Responses。错误由 responses_errors 统一分类并投影为 SDK 可解析的 SSE code。 -
python scripts/run_responses_compat.py --require-all在回环 uvicorn 服务上验证 Python sync/async 与 JS SDK，fixture 仅替换上游并保留实际池/状态/parser；测试依赖与 WebUI 隔离，Node/驱动缺失不能跳过。实际 HAR 只用于临时实时验收，禁止进入 fixtures/CI。
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.
- 9d ago Changed · +31 lines · +1,562 tokens per session 5effd1dfb67c
- 10d ago Changed · -44 lines · -51 tokens per session d9a26450ef02
- 19d ago Changed · +106 lines · +6,468 tokens per session b3b38675cabb
- 26d ago Changed · +12 tokens per session 983660cd240c
- 1mo ago Changed · -6 lines · -308 tokens per session a5fd525a67c8
- 1mo ago Changed · -1 lines · +52 tokens per session 3ca053077a54
- 1mo ago Changed · +91 tokens per session 3b321444fb70
- 1mo ago Changed · +11 lines · +255 tokens per session f403d5993687
- 2mo ago Changed · +5 lines · +240 tokens per session ac5d4aacb84e
- 2mo ago First seen · 2,648 lines · 33,836 tokens per session scan C 57080e8cfe08
deepseek-web2api-free AGENTS.md is an instructions file published in the GitHub repository snake-aabb-wtf/deepseek-web2api-free (218 stars, last pushed 9d ago), licensed Unlicense. It adds 42,157 tokens to every session, about $0.1686 per session on Opus 5.5. A static security scan graded it C with 3 findings (sends data to an external url, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
deepseek-web2api-free AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deepseek-web2api-free AGENTS.mdsnake-aabb-wtf/deepseek-web2api-free | Instructions file | 218 | 9d ago | Unlicense | C | 42,157 | Codex, OpenCode |
| 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 |