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/superjj007/csswitch/agents-mdgit clone --depth 1 https://github.com/SuperJJ007/CSSwitchWhat 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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
CSSwitch AGENTS.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 yesterday.
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.
What it actually says
CSSwitch Agent 规则入口
本文件只负责索引，不保存版本快照、测试结果或架构正文。
阅读顺序
- 所有任务先读安全规则和Git / worktree 规则。
- 再按任务读取
.agents/rules/下零或一项最接近的领域规则；没有匹配项时不强行套用。涉及文档创建、修改、引用或删除时读文档治理规则。 - 涉及版本、分支、worktree、验证状态或已知问题时，先实时复核，再参考
.agents/context/的日期化快照。 - 架构、运维、功能合同、历史证据和外部参考从文档总入口进入。
默认首轮只加载解决任务所需的一个索引和最多两份相关正文或 Context；需要更多证据时沿链接逐级展开，不预读全部 context、audit 或 evidence。正式独立审查额外读取 reviewing.md overlay，但不增加领域规则、索引、正文或 Context 的预算。
信息权威顺序
目标 artifact / runtime > tag 与公开 release > 当前源码和测试 > .agents/context/ > docs/ > memory / handoff。
.agents/rules/ 是 Agent 的稳定行为规则；.agents/context/ 只是可更新的当前状态索引；临时交接不得替代两者。
工作边界
- 未提交内容按用户数据保护；只读任务只允许检查和报告。
- commit、push、tag、release、替换已安装 App或运行真实 provider 测试均需明确授权。
- 真实 API Key、OAuth token、Keychain、SSH 私钥和账号数据库始终不得读取或回显；真实 provider 测试只能消费用户显式提供给隔离进程的输入，授权测试不等于授权检查凭证内容。
- 临时 handoff 放入
.agents/handoffs/，长期事实应进入 rules、context 或 docs。
收口纪律
- 同一个有界目标或候选的正式独立审查最多两轮：首轮集中发现问题，修复合并完成后只做一轮最终复审；不得因逐项修复反复启动新的 reviewer。详细规则见
reviewing.md。 - WIP 阶段不因每次小改动反复旋转或核对测试身份 hash；先完成目标内改动并冻结候选，再统一更新一次、验证一次。只有冻结后相关源文件再次变化或 validator 报告具体不一致时才重做。
- 始终围绕用户当前目标和预先声明的收口清单工作。目标外发现只有直接阻断当前结果的 P0 / P1 才可纳入本轮；其余记录并延后，不得演变成无上限加固或审查循环。
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.
- yesterday First seen · 32 lines · 702 tokens per session scan A 63527950f715
CSSwitch AGENTS.md is an instructions file published in the GitHub repository SuperJJ007/CSSwitch (452 stars, last pushed 9d ago), licensed MIT. It adds 702 tokens to every session, about $0.0035 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
claude-science-api-bridge AGENTS.md
Instructions for Jyx0208/claude-science-api-bridge, covering agent operating manual, prime directive, goal, repository map and success criteria.
academic-commercialization-agent AGENTS.md
Instructions for shuxiachai/academic-commercialization-agent, covering agents.md — working on this project, what it is, commands, hard conventions and where the reasoning lives.
Tianshu-harness CLAUDE.md
Instructions for huiliyi37/Tianshu-harness, covering 天枢 (tianshu) / rivet, build & test, architecture, conventions and known constraints.
cherry-studio AGENTS.md
AGENTS.md instructions for CherryHQ/cherry-studio, a project described as: AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs.
rikkahub AGENTS.md
AGENTS.md instructions for rikkahub/rikkahub, covering repository guidelines, project overview, build, test, and development commands, module structure and concepts.
writing-agent CLAUDE.md
Instructions for dongbeixiaohuo/writing-agent, covering 写稿 agent 核心路由指令（v0.10.0） and 路由顺序.