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 skills/caidaoli/ccload/sync-cliproxy-corenpx skills add caidaoli/ccLoad --skill sync-cliproxy-coregit 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/skills/caidaoli/ccload/sync-cliproxy-core)<a href="https://agentmods.dev/skills/caidaoli/ccload/sync-cliproxy-core"><img src="https://agentmods.dev/badge/skills/caidaoli/ccload/sync-cliproxy-core.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 | $0.00075 | $0.02637 |
| Opus 5 | $0.00037 | $0.01319 |
| Sonnet 5 | $0.00015 | $0.00527 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
sync-cliproxy-core 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 5d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
同步 CLIProxy 转换核心与渠道适配器
一次同步 CLIProxyAPI 的四协议纯转换核心、已登记 provider adapters 及其对应测试。保持 ccLoad Registry 和 provider wire 契约,不引入上游运行时系统。
默认调用 $sync-cliproxy-core 时,自动固定上游最新稳定版本,并在同一次操作中完成 core 与全部已登记 provider adapters 的比较、集成、来源更新和验证。不要把 provider adapters 留给第二次同步。用户明确指定 commit/tag 时使用指定目标;用户明确要求仅审计时保持只读。
原子同步契约
- core 与 provider adapters 必须来自同一 checkout、同一不可变 commit。
- 只生成一份变化清单,只更新一次来源 commit 和同步日期,只运行一套完成验证。
- 任一同步域无法移植、缺少匹配测试或验证失败时,整个同步未完成;不得只更新 core 后声称成功。
- 不提供隐式 core-only 降级。用户明确缩小范围时可以只审计,但不得把部分写入伪装成完整同步。
权威边界
- 先读仓库根目录
CLAUDE.md、internal/protocol/cliproxy/UPSTREAM.md、core snapshot manifest、provider adapter 语义边界和provider manifest。UPSTREAM.md是来源、固定提交和已落地状态的唯一事实源;core manifest 记录直接映射根、特殊映射、明确排除和最近一次 core/provider 原子差异的审查 blob,provider manifest 是 provider、逐文件映射、生产接线和契约测试的唯一 allowlist。 internal/protocol/registry.go定义四协议契约;internal/protocol/builtin/cliproxy_adapter.go处理通用输入验证、JSON/SSE 规范化和流帧封装;internal/protocol/cliproxy/providers/保存 provider-specific 纯转换。- provider 选择留在 ccLoad 请求上下文边界,按实际 wire dialect/AuthType 决定;不要把 provider 注册成第五种通用客户端协议。
- 不引入 CLIProxyAPI 的认证、配置、路由、缓存服务、插件、动态 Registry、executor 或网络刷新代码。Interactions 只有在 ccLoad 正式支持其线协议后才可登记。
- 不添加 CLIProxyAPI 运行时 Go module 依赖或
replace。源码继续使用ccLoad/internal/protocol/cliproxy/...导入路径。 - Registry 与 provider 边界测试是 ccLoad 兼容性权威。上游行为与本地线协议冲突时,修正根因并保留本地契约,不盲目覆盖。
同步流程
1. 预检
- 确认当前目录属于 ccLoad,并检查
git status --short。 - 保护已有修改。若工作区改动覆盖 core、providers、适配器、Registry、
go.mod、go.sum或UPSTREAM.md,先区分用户修改与本次同步;无法安全隔离时停止并说明冲突。 - 记录当前同步 commit 和目标 commit。
2. 固定目标
- 用户指定 commit/tag 时,解析成完整不可变 commit SHA。
- 用户未指定目标或只说“同步最新”时,自动查询
UPSTREAM.md记录仓库的远端 tags。以当前记录 tag 的非版本前缀和vMAJOR.MINOR.PATCH形状确定稳定 tag 系列,按语义版本选择最高版本;忽略预发布 tag,禁止按字典序或提交时间猜版本。 - 将选中的 tag 解引用为完整 commit SHA(等价于
<tag>^{commit})。记录并同步该 commit,而不是 annotated tag object;报告目标和变化范围后直接继续,不等待确认。 - 若无法从当前记录确定 tag 系列、找不到稳定 tag,或 tag 无法解析为 commit,停止并说明原因。禁止退回到浮动分支 HEAD。
- 若目标 SHA 与当前同步 SHA 相同,不改写
UPSTREAM.md的同步日期;运行确定性审计和验证后报告已是最新版本。 - 使用现有上游 checkout,或在临时目录克隆
UPSTREAM.md记录的仓库。core、provider 生产源码与测试必须全部来自这个 checkout 的同一个 commit。
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 116 lines · 75 tokens per session scan A 004730896ad2
sync-cliproxy-core is a skill published in the GitHub repository caidaoli/ccLoad (403 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 2,637 once invoked, about $0.0004 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 skills, from other repositories
problem-framing
1flowbase 需求对齐、会导向产品决策的现状诊断与动工前决策 Skill。用于功能、缺陷、交互、重构、规则、文档、架构、数学或算法表达、状态、权限、数据、API contract 或跨前后端需求;也用于诊断为什么两个流程不一致、能力为何缺失或不可编辑、职责应放在哪个入口、当前设计是否应改变。从证据中收敛现状、需求分析、保守 / 平衡 / 激进三个方向与唯一建议,再选择 Single Issue 或两层 Issue Tree。确认前不实现;只有不影响产品 / 设计决策的事实查询、机械精确改动或用户明确要求直接实现时可跳过。.
qa-evaluation
Evidence-driven QA evaluation for 1flowbase dev acceptance, PR merge gates, project health gates, regression, stale or incompatible test expectation triage, delivery, full-project and AI code audits, quality gate routing, i18n/multilingual key-value hygiene, frontend/backend contracts, console settings registry and…
github-solution-research
Use when a concrete engineering problem, bug, integration failure, dependency issue, unclear API usage, implementation blocker, or tool/capability need may already have a proven solution in GitHub open-source projects, issues, pull requests, discussions, code, examples, or release notes. Use it to find suitable…
test-driven-development
Use when implementing 1flowbase features, bug fixes, refactors, backend APIs, state transitions, permissions, contract changes, or behavior changes that can be covered by automated tests. For a Single Issue, run the minimum failing test before implementation. For an Issue Tree, define the finite acceptance matrix and…
backend-development
Use for 1flowbase backend implementation in api/: building, fixing, refactoring, or code-reviewing Rust/Axum APIs, routes, services, repositories, storage adapters, migrations, domain models, state transitions, write paths, module boundaries, permissions, backend-registered console settings and their API scopes…
frontend-development
Use for 1flowbase frontend implementation in web/: building, fixing, refactoring, or code-reviewing UI pages, app shell, routes, workspace flows, node UI, schema UI, i18n resources, responsive layout, visual structure, ECharts/reporting UI, low-code JS Block chart primitives, or frontend state boundaries. Use after…