Borrowing it
Nothing to install: this file belongs to dainsiahtill-dev/Polaris. 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/dainsiahtill-dev/Polaris/main/CLAUDE.mdgit clone --depth 1 https://github.com/dainsiahtill-dev/PolarisWrote 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/dainsiahtill-dev/polaris/claude-md)<a href="https://agentmods.dev/instructions/dainsiahtill-dev/polaris/claude-md"><img src="https://agentmods.dev/badge/instructions/dainsiahtill-dev/polaris/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/dainsiahtill-dev/polaris/claude-md"><img src="https://agentmods.dev/badge/instructions/dainsiahtill-dev/polaris/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 | $0.05242 | $0.05242 |
| Opus 5.5 | $0.02097 | $0.02097 |
| Sonnet 5.5 | $0.01048 | $0.01048 |
| Haiku 4.5 | $0.00524 | $0.00524 |
Grade A, and why
Polaris 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 7d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
主线研发(用户决定,2026-10-20)
所有源码修改与提交直接在主仓 main 进行,不再创建开发分支或开发 worktree。已存在的冻结副本只读保留证据;测试与审计资料继续放在 ~/.polaris/。
本文件用于指导在本仓库工作的 AI 编码代理。仅保留可执行、可验证的技术约束。
必用MCP和Skill: 充分利用codegraph MCP和superpowers,必要时需要使用Playwright来真实跑测试和审计。
-1) 强制工具链:RTK + CodeGraph + Caveman
- RTK:每条 shell 命令及每个 chained segment 都必须以
rtk开头。优先使用 RTK 原生命令;无对应命令时使用rtk proxy <command>。裸 shell 命令只允许用于明确的 RTK 故障诊断。 - CodeGraph:源码发现、架构/调用链/影响分析、代码审查及修改前上下文必须先调用
mcp__codegraph__codegraph_explore。返回源码视为已读,禁止再用rg/reader 重复读取;只有 CodeGraph 未覆盖、未索引或明确不可用时,才允许使用 RTK fallback,并记录原因。 - Caveman:默认启用
caveman的full模式,压缩过程更新与结果,删除重复叙述和无关日志,但必须保留精确技术名、错误文本、命令、验证数字、风险与未完成门禁。安全警告、不可逆操作和可能产生歧义的多步流程恢复完整表达。 - 三者必须共同使用,不能用其中一个替代另两个。标准顺序:加载适用 Skill -> CodeGraph 定位/审计 -> RTK 执行与验证 -> Caveman 压缩汇报。
0) 后端权威入口(2026-03-22)
- 用户事件降噪:成功的 stage/task/worker 心跳仅用于保活与审计,禁止刷入普通“最近事件”或重复通知。展示过滤必须在窗口截取之前;不删底层事实,不隐藏心跳失败/告警、阶段切换、工具结果或交付进展。仅有保活或当前窗口缺少调用证据,不能宣称模型从未执行;前端验收需真实 runtime.v2 推送、无 reload/产品轮询。
- 对于任何
src/backend任务,必须先读src/backend/AGENTS.md。 - 统一架构执行标准入口:
src/backend/docs/AGENT_ARCHITECTURE_STANDARD.md。 - 后端强制规则:
Cell开发先复用已有 Cell 公开能力;所有新开发必须基于KernelOne底座能力与契约链路。 - 若本文件与
src/backend/AGENTS.md或src/backend/docs/AGENT_ARCHITECTURE_STANDARD.md存在冲突,以后两者为准。
当前工程主线
- 新工程运行的唯一 owner 是现有
roles.runtime.public.engineering_service.EngineeringRunService。HTTP、CLI、UI、取消、恢复与错误路径共用该服务,不新增 Cell、任务表、ledger 或第二 controller。 - 默认
workflow=direct,Director 读取目标、调用工具、根据真实结果继续工作;PM/Chief Engineer 按需只读咨询。显式workflow=collaborative才执行 PM、Chief Engineer、Director 协作;未调用角色显示not_called。咨询一层返回,不递归派生总控;讨论不创建工程 run。 - PM/CE 使用可读文本提供规划、设计或审阅。新运行不要求 PM 合同、CE portfolio/blueprint、handoff/hash、OBL/covers 图、semantic patch、Task Market、JobToken/DEO/Run Ledger 旧链准入,也不受旧一 turn 一 batch 规则约束。普通编译/测试失败回到同一 Director,不自动 deterministic repair 或重启规划。
- 工具授权来自 host 持久化且不可由模型扩大的
PermissionScope、当前 profile、预算与 deadline;显式空权限保持为空。归一化后仍须检查真实路径/symlink/允许根,经 KFS 读写和 OS/process sandbox 执行命令;不支持 containment 时明确拒绝,禁止裸跑。PM/CE/QA 默认只读,同 workspace 仅一个源码写入者。 - 唯一工程事实记录是
<workspace>/.polaris/runtime/engineering/sessions.sqlite3,保存运行、事件、真实工具观察和验证;新运行不写旧 TaskBoard/TaskMarket/Run Ledger/role-session 镜像。保留 runtime.v2/Nats-JetStream、ContextOS 最终 provider request、UTF-8、实例 workspace 绑定与 storage 单根。 - 角色回复结束与
completed不等于accepted。实际检查必须绑定当前源码;用户已声明检查必须保留,未声明时由 Director 结合实际工程选择并实际执行验证。空检查、模型自报、快照条数或 QA 文本不得冒充通过;任务要求的独立 QA 必须审查同一当前候选,拒绝后继续同一任务。 - 恢复使用原身份、workspace、原始权限与 deadline,并重新校验当前 host policy;保留失败、interrupted/UNKNOWN 和未知效果,不自动重放可能已执行的命令或写入。旧 ID 不升级为新 run;历史按
engine_version只读,旧在途运行留在原冻结 owner,不在新进程恢复旧写入口。 - 旧 Factory/RoleRuntimeService/execute_role_session/RoleExecutionKernel 写准入与自动 fallback 退役;历史解码器、只读查询与显式可选技术工具可保留,禁止据此声称历史源码已全部删除。旧规范仅解释旧记录,不能重新约束新运行。底层 hash 可用于证据/快照完整性,不能要求模型填写业务 hash。真实 HTTP 次数与费用仅用物理证据,未知保持 UNKNOWN。
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.
- 7d ago Changed · +21 tokens per session fbb0f933e3f3
- 15d ago Changed · -25 lines · +246 tokens per session e78afe178a8c
- 16d ago Changed · -523 lines · -12,656 tokens per session 51a94f4d91ea
- 1mo ago Changed · +1 lines · +112 tokens per session 80341228cc84
- 2mo ago First seen · 724 lines · 17,519 tokens per session scan A 373cdf1b75d5
Polaris CLAUDE.md is an instructions file published in the GitHub repository dainsiahtill-dev/Polaris (102 stars, last pushed 3d ago), licensed MIT. It adds 5,242 tokens to every session, about $0.0210 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.
Polaris CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Polaris CLAUDE.mddainsiahtill-dev/Polaris | Instructions file | 102 | 3d ago | MIT | A | 5,242 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |