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 agentmods add instructions/caidaoli/ccload/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.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 | $0.15495 | $0.15495 |
| Opus 5 | $0.07748 | $0.07748 |
| Sonnet 5 | $0.03099 | $0.03099 |
| Haiku 4.5 | $0.01550 | $0.01550 |
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 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.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
ccLoad:Claude/OpenAI/Gemini/Codex 多协议 API 网关(渠道/Key/URL 选择 + 故障切换 + 协议转换 + 成本计量)。 本文件是 AI 操作手册——只记命令、硬约束、反直觉机制与入口;展开细节读对应代码。
命令
必须 -tags sonic;环境变量见 .env。
make build # 构建(注入版本号+strip)
make dev # 开发运行
bash .agents/skills/sync-cliproxy-core/scripts/verify.sh --tests # 协议快照审计+定向测试
bash .agents/skills/ccload-release/scripts/release.sh --self-test # 发布脚本自检
go test -tags sonic ./internal/...
make race-fast # 高价值 race 子集
make race # 全量 race(可用 RACE_P/RACE_PARALLEL 调并行度)
make verify-web # 前端验证(含 node:test)
golangci-lint run ./... # 提交前必须零警告
测试策略
- 迭代只跑受影响包:
go test -tags sonic ./internal/app -run 'TestXxx';提交前全量./internal/...。Go 测试、make verify-web、make build、lint 相互独立,可并行 - 不用
-count=1,除非排查缓存或不稳定测试 - 积极
t.Parallel():并行测试必须独立 Store/Server、随机监听端口、局部 mock,不共享可变 fixture;调用t.Setenv/t.Chdir,或修改进程环境、工作目录、http.DefaultTransport、全局模型目录、包级 session/cache、全局 goroutine 计数的测试必须串行 - 优先并行化含 sleep、deadline、轮询、异步日志等待的高耗时测试;不为凑并行数改纯解析微测试
- 并行化前后同命令计时(
/usr/bin/time -p go test -tags sonic -count=1 ./internal/app),收益属噪声就撤销;新增/调整并行测试后跑go test -race -tags sonic -count=1 -shuffle=on ./internal/app
代码规范(硬约束)
- 必须
-tags sonic;用any,不用interface{} - YAGNI,拒绝过度工程;Fail-Fast:配置错误
log.Fatal()退出 - Context:
defer cancel()无条件调用,用context.AfterFunc监听取消 - lint 启用 errcheck/govet/staticcheck/unused/revive/bodyclose(gosec 已禁)
- Web 单选下拉必须可搜索:禁止让原生
<select>直接出现在最终 UI,统一由searchable-select.js增强并复用createSearchableCombobox;原生<select>只允许作为隐藏的表单/业务值载体,禁止页面私造下拉。动态选项、禁用态、原生input/change、表单提交、键盘/ARIA 与<dialog>顶层菜单都必须保留;多选控件未提供可搜索实现前禁止新增
架构与入口
internal/app/ HTTP+业务:proxy_* / admin_* / selector_* / *_cache / *_service
internal/protocol/ 协议契约与注册;builtin/ 是 ccLoad 适配层;cliproxy/ 是上游转换核心快照
internal/storage/ 存储(factory/hybrid_store/sync_manager/migrate;sql/ sqlite/)
internal/cooldown/ 冷却决策 internal/util/ classifier/cost_calculator/money/...
internal/{model,config,version,testutil}/ web/ 管理后台前端(HTML+assets/{css,js,locales})
www/ 独立介绍站(`make www-setup` 复制共享资源后可脱离仓库部署,别和 web/ 混淆)
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 · +3 lines · +422 tokens per session c26950346f1e
- yesterday Changed · +886 tokens per session 45af0e22230e
- 5d 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 (403 stars, last pushed today), licensed MIT. It adds 15,495 tokens to every session, about $0.0775 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 instructions, from other repositories
1flowbase AGENTS.md
AGENTS.md instructions for taichuy/1flowbase, covering 记忆, 用户偏好, 本项目相关skill在, 本项目 skills and 质量控制.
1flowbase CLAUDE.md
Claude Code instructions for taichuy/1flowbase, covering 记忆 and 用户偏好.
1flowbase GEMINI.md
Gemini CLI instructions for taichuy/1flowbase, covering 记忆 and 用户偏好.
9router CLAUDE.md
Claude Code instructions for decolua/9router, covering claude.md, what this is, commands, architecture and request flow (the thing to understand first).
OmniRoute CLAUDE.md
Claude Code instructions for diegosouzapw/OmniRoute, covering claude.md, worktree isolation — claude code specifics, cross-session safety — claude code specifics, superpowers / planning artifacts — path overrides and scratch / temporary files — use artifacts/, not /tmp.
OmniRoute copilot-instructions.md
Copilot instructions for diegosouzapw/OmniRoute, a project described as: Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback…