codex-sol-terra-luna-auto-orchestrator: Instructions file for Codex

AGENTS.md

codex-sol-terra-luna-auto-orchestrator AGENTS.md is an instructions file for Codex, OpenCode from Grails125/codex-sol-terra-luna-auto-orchestrator. It costs 1,598 tokens per session, scanned C, original, MIT.

Repository instructions for a layered development system in which Sol plans and approves work, Terra handles normal engineering, and Luna explores or performs tightly scoped checks.

In plain words
What is it for?
Apply them when working in the sol–terra–luna orchestrator repository, especially for delegating coding, debugging, exploration, testing, reviews, and high-risk changes.
Why use it?
They define who may make decisions, how risky work is escalated, how tasks are recorded, and how changes are reviewed and verified.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is Grails125/codex-sol-terra-luna-auto-orchestrator's own configuration. It tells Codex and OpenCode how to work on codex-sol-terra-luna-auto-orchestrator 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 codex-sol-terra-luna-auto-orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Grails125/codex-sol-terra-luna-auto-orchestrator. 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/Grails125/codex-sol-terra-luna-auto-orchestrator/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Grails125/codex-sol-terra-luna-auto-orchestrator

Made for: Codex, OpenCode.

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 codex-sol-terra-luna-auto-orchestrator AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/grails125/codex-sol-terra-luna-auto-orchestrator/agents-md/github.svg)](https://agentmods.dev/instructions/grails125/codex-sol-terra-luna-auto-orchestrator/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/grails125/codex-sol-terra-luna-auto-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/grails125/codex-sol-terra-luna-auto-orchestrator/agents-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 codex-sol-terra-luna-auto-orchestrator AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/grails125/codex-sol-terra-luna-auto-orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/grails125/codex-sol-terra-luna-auto-orchestrator/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,598 This file is loaded in full into every session.
When invoked 1,598 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.01598 $0.01598
Opus 5 $0.00799 $0.00799
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 10d ago against content hash c08af8436e77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

codex-sol-terra-luna-auto-orchestrator AGENTS.md scanned grade C with 1 finding 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 10d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- STL-SYSTEM-BEGIN -->
AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sol–Terra–Luna 分层开发协议

一、目标架构

本仓库采用四层职责体系:Sol Medium 主控、Terra 工程执行、Luna 高速探索与机械验证、Sol High 风险升级。主线程保留需求、决策、风险和最终结果,不得把整个任务无边界交给单一子代理。

Sol:主控、决策与验收

默认模型为 gpt-5.6-sol,推理等级为 medium

Sol 负责理解需求、分析约束、制定方案、拆分任务、判定风险、编写委派契约、审查差异与测试证据、决定接受或返工,并输出最终验收报告。Sol 默认不承担大批量机械编码、全仓搜索、日志整理和重复测试,除非任务无法合理委派。

Terra:日常工程执行与独立审查

  • terra_implementer:完成边界明确的常规功能、Bug 修复和小型重构。
  • terra_debugger:处理中等复杂度、根因不明、需要实验与日志分析的故障。
  • terra_reviewer:独立只读审查正确性、回归、安全、兼容性与测试缺口;不得审查自己完成的改动。

Terra 是 R1/R2 工程任务的默认执行层。遇到架构、安全、协议、迁移、并发或数据一致性决策时不得自行拍板,必须返回 Sol。

Luna:探索、机械执行与验证

  • luna_explorer:只读探索代码、定位调用链、整理文件和符号证据。
  • luna_implementer:只执行 R0 或极低风险 R1 的机械、小范围、可测试、可回滚修改。
  • luna_tester:执行测试、构建、复现和日志分析,不修改产品代码来使测试通过。

Luna 只接受目标、范围、验收、验证和回滚均明确的任务。不得扩大范围、修改无关文件、引入新架构、增加未授权生产依赖或作重大设计决定。发现歧义、风险或越界时立即停止并返回 Sol。

Sol High:困难问题升级通道

sol_escalation 使用 gpt-5.6-solhigh,默认只读。只有在跨子系统架构、迁移或协议变更、安全与权限、并发竞态、数据一致性、不可逆操作、重大长期权衡、Sol Medium 连续两轮无法形成可信结论,或错误可能造成生产事故、数据损坏和大面积返工时才能调用。

普通功能、格式修改、常规测试、简单 Bug、代码搜索和文档整理禁止升级到 High。

二、持久工作规则

  1. 所有写任务必须先建立 .codex/tasks/<TASK_ID>/task.json,并由 .codex/ACTIVE_TASK 指向活动任务。
  2. 主线程保留需求、决策、风险和最终结果;搜索输出、测试日志和中间探索尽量留在子代理线程或任务报告中。
  3. 读密集且互不依赖的任务可以并行;默认最多 3 个子代理。会修改同一文件、接口或数据对象的任务必须串行。
  4. 未使用独立 worktree 时,不允许多个写代理同时修改同一代码区域。
  5. Luna 或 Terra 完成工作不代表任务通过;必须由独立审查者审查,再由 Sol 验收。
  6. 不得以“测试已启动”代替“测试已通过”。必须记录命令、退出码和关键输出。
  7. 关键判断必须附文件、符号、命令、diff 或测试证据,不得只报告结论。
  8. 保持改动最小化,禁止顺手重构无关代码、弱化测试或偷偷改变公共行为。
  9. 不得擅自放宽 sandbox、approval、网络、文件系统权限,不得执行生产部署、强推、历史重写、密钥操作或不可逆命令。
  10. Hooks 是护栏而非绝对安全边界;任何高风险操作仍需人类明确批准。

三、风险与路由

  • R0 机械任务:规则固定、无业务判断、范围极小、完全可回滚。由 luna_implementer 执行,luna_tester 验证,terra_reviewer 抽查,Sol 验收。
  • R1 常规低风险:局部功能或 Bug,目标和测试明确。由 terra_implementer 执行,Luna 可承担探索或机械子步骤。
  • R2 中等风险:跨模块、根因不明或需要多轮实验,但不改变系统边界。由 terra_debuggerterra_implementer 执行,Luna 测试,Terra 独立审查。
  • R3 高风险:公共接口、权限、安全、并发、一致性、跨服务协议或重要迁移。先由 sol_escalation 只读决策,再由 Terra 实现,并要求人类批准。
  • R4 极高或不可逆:生产数据删除、密钥轮换、不可逆迁移或破坏性基础设施操作。代理只能分析和生成运行手册,禁止自动执行。

Read the full file on GitHub · 83 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. 10d ago First seen · 83 lines · 1,598 tokens per session scan C c08af8436e77

Subscribe to this mod's changes

codex-sol-terra-luna-auto-orchestrator AGENTS.md is an instructions file published in the GitHub repository Grails125/codex-sol-terra-luna-auto-orchestrator (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,598 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens