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.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 | $0.34076 | $0.34076 |
| Opus 5 | $0.17038 | $0.17038 |
| Sonnet 5 | $0.06815 | $0.06815 |
| Haiku 4.5 | $0.03408 | $0.03408 |
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 today.
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 — 2,653 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — DeepSeek Chat API Proxy (Preview)
本文档面向后续维护本项目的 AI 智能体，完整阐述项目的实现原理、协议细节、代码架构和已知问题。请先全文阅读本文档再开始任何修改。
v3.0.0 → v3.3.2 变更摘要
v3.3.2（2026-09-05）：WebUI 请求趋势图修复（stats 历史采样 AttributeError）
- 合并 PR #14：
stats_history.StatsHistory.snapshot()读取了StatsSnapshot上不存在的avg_latency_ms属性 → 每次快照抛AttributeError，被采样线程except Exception: pass静默吞掉 →/admin/api/history自进程启动起永远返回points: []。修复为与/admin/api/stats端点一致的自算平均：total_latency_ms / total_requests（零请求时 0.0）（详见 docs/release-notes/v3.3.2.md） - 测试：新增
tests/test_stats_history.py（4 例：正常取值 / 零请求不除零 / 严格对象回归测试——snapshot 只允许触碰真实存在字段 / max_points 截断）
v3.3.1（2026-08-11）：防轰炸加固 + 双语文档
- 合并 PR #11（防账号静音）：上游并发上限
DEEPSEEK_MAX_CONCURRENCY(默认2) + 增量(delta)prompt + 静音识别(UserMutedError→429) + 重试 parent 清理 +SESSION_CACHE_TTL默认 600→1800（详见 docs/release-notes/v3.3.1.md） - 文档：新增
README_en.md英文完整版 + 双语顶部语言切换链接；删除 README 顶部的版本日志块（changelog 归 docs/release-notes/）；README/AGENTS.md 补「非交互式账号池配置」（accounts.json schema + 自动化配置 checklist）
v3.0.0 → v3.2.4 变更摘要
v3.2.4（2026-08-11）：上游并发上限 + 增量 prompt（防历史泛滥/防静音）
- 并发上限：
DEEPSEEK_MAX_CONCURRENCY（默认2）全局限制同时进行中的上游请求（跨账号），超出的请求排队等待而非 503（_UPSTREAM_LIMITERBoundedSemaphore，在_acquire()中先于pool.acquire()获取、AcquiredAccount.release()幂等释放）。编码智能体（opencode/Claude Code）会并行派出多个子 agent，此前会并发轰炸上游诱发账号静音 - 增量 prompt（delta）：
ChatSession.sent_prompt记录上一轮实际发送的完整 prompt；AcquiredAccount.prepare_prompt()对客户端重发的完整历史做前缀比对——历史是上一轮的延续时只把新增尾部发给上游（上下文由 parent 链在服务端维系）；完全重复视为同一轮重试（重发）；历史发散则失效缓存换新会话。此前每次请求都重发整段历史，DeepSeek 会话中每条消息都内嵌之前所有轮次（平方级膨胀，自动化特征显著，是账号被静音的重要诱因） - 静音识别：上游对账号级处罚返回 200 + 普通 JSON
{"data":{"biz_code":5,"biz_msg":"user is muted","mute_until":...}}（非 SSE，旧代码解析为"空响应"）。UserMutedError（RateLimitError子类）在流式/非流式两条路径识别并立即抛出（跳过退避重试），映射 429 并带解封时间 - 重试带清理：rate-limit/空响应换新会话重试时不再携带旧会话的
parent_message_id（新会话里的无效 parent 会导致上游再次空响应） - SESSION_CACHE_TTL 默认 600 → 1800：长编码会话（agent 10 分钟+ 空闲）不再频繁被迫新建上游会话
- 完整清单：
docs/release-notes/v3.2.4.md
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.
- today Changed · +5 lines · +240 tokens per session ac5d4aacb84e
- 7d 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 (108 stars, last pushed yesterday), licensed Unlicense. It adds 34,076 tokens to every session, about $0.1704 per session on Opus 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.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.