Polaris: Instructions file for Claude Code

CLAUDE.md

Polaris CLAUDE.md is an instructions file for Claude Code from dainsiahtill-dev/Polaris. It costs 5,242 tokens per session, scanned A, original, MIT.

A set of repository instructions for coding agents working on the Polaris project. It defines required tools, project entry points, architecture rules, and completion checks.

In plain words
What is it for?
Use it when an agent works in the Polaris repository, especially on backend code, automated repairs, architecture changes, or unattended tasks.
Why use it?
Large projects need consistent rules for finding code, making changes, running checks, and deciding when work is actually complete. These instructions give the agent those project-specific constraints.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is dainsiahtill-dev/Polaris's own configuration. It tells Claude Code how to work on Polaris itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Polaris configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/dainsiahtill-dev/Polaris/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dainsiahtill-dev/Polaris

Made for: Claude Code.

Wrote 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.

agentmods badge for Polaris CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dainsiahtill-dev/polaris/claude-md/github.svg)](https://agentmods.dev/instructions/dainsiahtill-dev/polaris/claude-md)
Your own site
<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.

agentmods 80×15 button for Polaris CLAUDE.md

Your own site · 80×15
<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>
Per session 5,242 This file is loaded in full into every session.
When invoked 5,242 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash fbb0f933e3f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

CLAUDE.md · 177 lines

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

  1. 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。
  2. 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。
  3. 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。
  4. 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。
  5. 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。
  6. 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。
  7. 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。
  8. 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。

Read the full file on GitHub · 177 lines

Changes

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.

  1. 7d ago Changed · +21 tokens per session fbb0f933e3f3
  2. 15d ago Changed · -25 lines · +246 tokens per session e78afe178a8c
  3. 16d ago Changed · -523 lines · -12,656 tokens per session 51a94f4d91ea
  4. 1mo ago Changed · +1 lines · +112 tokens per session 80341228cc84
  5. 2mo ago First seen · 724 lines · 17,519 tokens per session scan A 373cdf1b75d5

Subscribe to this mod's changes

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.

Related

Polaris CLAUDE.md compared with instructions from other repositories

Polaris CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Polaris CLAUDE.mddainsiahtill-dev/PolarisInstructions file1023d agoMITA5,242Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode