Borrowing it
Nothing to install: this file belongs to caidaoli/ccLoad. 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/caidaoli/ccLoad/master/CLAUDE.mdgit clone --depth 1 https://github.com/caidaoli/ccLoadWrote 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/caidaoli/ccload/claude-md)<a href="https://agentmods.dev/instructions/caidaoli/ccload/claude-md"><img src="https://agentmods.dev/badge/instructions/caidaoli/ccload/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/caidaoli/ccload/claude-md"><img src="https://agentmods.dev/badge/instructions/caidaoli/ccload/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 | $0.01392 | $0.01392 |
| Opus 5.5 | $0.00557 | $0.00557 |
| Sonnet 5.5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
ccLoad CLAUDE.md 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 17d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
ccLoad 是 Claude/OpenAI/Gemini/Codex 多协议 API 网关，负责渠道选择、故障切换、协议转换与成本计量。
工作方式
- 修改任务完成到实现、相关验证及本次引入问题的修复；常规本地操作按现有授权连续执行。
- 按下表读取与当前改动有关的契约。新增或修正规则写入对应专题，根文件只保留通用约束与入口。
- 发布使用仓库
ccload-release；CLIProxyAPI 核心及 provider adapter 的同步/同步审计使用sync-cliproxy-core。 - 上游参照源码优先用本机 checkout：CLIProxyAPI
~/Source/go/CLIProxyAPI、sub2api~/Source/go/sub2api（~/Source即~/Share/Source）。checkout 不钉提交，对照时按专题文档或internal/protocol/cliproxy/UPSTREAM.md记录的提交用git -C <repo> show <commit>:<path>读，不读 HEAD；本机不存在时按记录的仓库与提交获取。
命令与验证
Go 构建和测试必须带 -tags sonic（Makefile 已处理）。环境变量契约见 .env.example（容器部署见 .env.docker.example）；本地 .env 被 gitignore，仅作个人覆盖。
make build # 构建并注入版本
make dev # 开发运行
go test -tags sonic ./internal/app -run 'TestXxx' # 受影响测试
go test -tags sonic ./internal/...
make verify-web # 前端验证，含 node:test
make race-fast # 并发相关改动；全量使用 make race
golangci-lint run ./... # Go 改动提交前零警告
- 迭代运行受影响包；Go 改动提交前运行全量
./internal/...与 lint，前端改动运行make verify-web。 - 不用
-count=1，除非排查缓存、不稳定测试或测量性能。独立检查可并行。 - 调整测试并行度时读 测试并行化。发布和核心同步的专属验证命令见各自技能。
通用代码约束
- 用
any；配置错误 fail-fast；defer cancel()无条件调用，取消监听用context.AfterFunc。 - lint 启用 errcheck/govet/staticcheck/unused/revive/bodyclose，gosec 已禁。
- JSON 重复 key 按
encoding/json后者胜出，不加检测、拒绝或兼容兜底，审查也不作为问题；只有改写与渲染不一致时才就地收敛（见ordered_json.go）。 - Web 单选下拉必须可搜索：统一由
searchable-select.js增强并复用createSearchableCombobox；原生<select>仅作隐藏的表单/业务值载体。保留动态选项、禁用态、input/change、表单提交、键盘/ARIA 与<dialog>顶层菜单；多选控件未提供可搜索实现前禁止新增。
任务入口
路径相对仓库根目录；下表省略目录的 Go 文件位于 internal/app/。只读取相关专题；上游文档按提供商分节。
| 任务 | 代码入口与契约 |
|---|---|
| 代理、SSE、重试、冷却、取消 | proxy_handler.go:HandleProxyRequest → runProxyAttemptLoop → proxy_forward.go / proxy_stream.go；代理契约 |
| Responses WebSocket | proxy_responses_websocket.go、responses_execution_session.go；代理契约及 Codex 契约 |
| 渠道/Key/URL、模型后缀、多模态回退 | selector*.go、key_selector.go、url_selector.go；路由契约 |
| 上游认证、请求指纹、provider wire | 各提供商 *_wire.go / *_credentials.go / internal/*auth/；上游契约 |
| Registry 与协议转换 | internal/protocol/registry.go → builtin/register.go → builtin/cliproxy_adapter.go；转换边界，快照来源见 internal/protocol/cliproxy/UPSTREAM.md |
| 计费、访问控制、OAuth 额度 | internal/util/cost_calculator.go、internal/oauthcost/、oauth_quota_cost.go；计费契约 |
| 系统设置、超时、连接、存储与迁移 | config_service.go、internal/storage/；运行与存储契约；写库后按改动失效 InvalidateChannelListCache / InvalidateAPIKeysCache |
| Admin API、管理账户与定时任务 | admin_types.go → admin_<feature>.go → server.go:SetupRoutes；账户核心为 channel_management_service.go；管理与定时任务 |
| 发布、容器与进程内更新 | .agents/skills/ccload-release/SKILL.md；更新机制 |
| 管理后台 / 独立介绍站 | web/ 是管理后台；www/ 是独立介绍站，make www-setup 复制共享资源后可独立部署 |
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.
- 17d ago Changed · -75 tokens per session a9df341cd0f8
- 23d ago Changed · +2 lines · +173 tokens per session 2c1e56626e04
- 1mo ago Changed · +26 tokens per session b493c34940b9
- 1mo ago Changed · -127 lines · -14,227 tokens per session 2c046d0f7f93
- 1mo ago Changed · +3 lines · +422 tokens per session c26950346f1e
- 1mo ago Changed · +886 tokens per session 45af0e22230e
- 1mo ago First seen · 175 lines · 14,187 tokens per session scan A 5cec851f9e9b
ccLoad CLAUDE.md is an instructions file published in the GitHub repository caidaoli/ccLoad (428 stars, last pushed today), licensed MIT. It adds 1,392 tokens to every session, about $0.0056 per session on Opus 5.5. 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 instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.