agentmods.dev

Polaris: Instructions file for Gemini CLI

GEMINI.md

Polaris GEMINI.md is an instructions file for Gemini CLI from dainsiahtill-dev/Polaris. It costs 905 tokens per session, scanned A, original, MIT.

A repository guide for Gemini CLI, an AI coding assistant, that explains how work should run in the Polaris project. It mirrors the project's other agent instruction files rather than adding separate rules.

In plain words
What is it for?
Use it when Gemini CLI is planning, changing, testing, or reviewing Polaris code, especially when work involves shared engineering runs, role-based consultation, or sandboxed tools.
Why use it?
It gives the assistant one place to find the project's workflow, permissions, storage, testing, and collaboration rules. This helps prevent conflicting run paths, unsafe file or command access, and outdated task records.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is dainsiahtill-dev/Polaris's own configuration. It tells Gemini CLI 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 →

not rated 102repo +1 3d ago A scan 905 tokens original MIT
View source ↗ dainsiahtill-dev/Polaris
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/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/dainsiahtill-dev/Polaris

Made for: Gemini CLI.

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 GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dainsiahtill-dev/polaris/gemini-md/github.svg)](https://agentmods.dev/instructions/dainsiahtill-dev/polaris/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/dainsiahtill-dev/polaris/gemini-md"><img src="https://agentmods.dev/badge/instructions/dainsiahtill-dev/polaris/gemini-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 GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dainsiahtill-dev/polaris/gemini-md"><img src="https://agentmods.dev/badge/instructions/dainsiahtill-dev/polaris/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 905 This file is loaded in full into every session.
When invoked 905 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 $0.00905 $0.00905
Opus 5.5 $0.00362 $0.00362
Sonnet 5.5 $0.00181 $0.00181
Haiku 4.5 $0.00090 $0.00090

Measured 15d ago against content hash 3627bab09996, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Polaris GEMINI.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 15d 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.

GEMINI.md · 17 lines

What it actually says

Gemini Repository Playbook

本文件是 AGENTS.md 与 CLAUDE.md 的镜像入口，不引入独立规则。后端任务先读 后端规则 和 架构标准。

工程主线（2026-10-21）

  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。

所有源码直接在主仓 main，不创建开发分支/worktree；审计资料放 ~/.polaris/。文本显式 UTF-8；shell 每段使用 RTK；源码/架构/调用影响先 CodeGraph；使用适用 superpowers 与压缩报告。保留 Cell public/internal 边界、KernelOne 技术复用、真实权限、单 runtime 根、最终请求审计、runtime.v2、实例隔离与证据先于结论。不得修改生成目标掩盖平台缺陷。

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. 15d ago First seen · 17 lines · 905 tokens per session scan A 3627bab09996

Subscribe to this mod's changes

Polaris GEMINI.md is an instructions file published in the GitHub repository dainsiahtill-dev/Polaris (102 stars, last pushed 3d ago), licensed MIT. It adds 905 tokens to every session, about $0.0036 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 2026-10-22.

Building agentsPlanning
Related

Polaris GEMINI.md compared with instructions from other repositories

Polaris GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Polaris GEMINI.mddainsiahtill-dev/PolarisInstructions file1023d agoMITA905Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, 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