agentmods.dev

orbit-agent-workbench: Instructions file for Codex

AGENTS.md

orbit-agent-workbench AGENTS.md is an instructions file for Codex, OpenCode from gaowei90098-creator/orbit-agent-workbench. It costs 550 tokens per session, scanned A, original, MIT.

Project instructions for Orbit, a workbench for coordinating a main coding agent and smaller helper agents. It describes the repository, its current product direction, and the records that must be checked before changing code.

In plain words
What is it for?
Use them before editing Orbit to read the project memory, compare the correct remote branch, preserve the task-planning and helper-agent architecture, and ignore local-only build and worktree folders.
Why use it?
They prevent changes from being based on outdated project assumptions, such as treating an old repository or earlier product name as current.

Instructions file for CodexOpenCode

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

This is gaowei90098-creator/orbit-agent-workbench's own configuration. It tells Codex and OpenCode how to work on orbit-agent-workbench 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 orbit-agent-workbench configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/gao90098/Desktop/Orbit.app.

not rated 2repo 2mo ago A scan 550 tokens original MIT
View source ↗ gaowei90098-creator/orbit-agent-workbench
Reuse

Borrowing it

Nothing to install: this file belongs to gaowei90098-creator/orbit-agent-workbench. 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/gaowei90098-creator/orbit-agent-workbench/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gaowei90098-creator/orbit-agent-workbench

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 orbit-agent-workbench AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gaowei90098-creator/orbit-agent-workbench/agents-md.svg)](https://agentmods.dev/instructions/gaowei90098-creator/orbit-agent-workbench/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gaowei90098-creator/orbit-agent-workbench/agents-md"><img src="https://agentmods.dev/badge/instructions/gaowei90098-creator/orbit-agent-workbench/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 550 This file is loaded in full into every session.
When invoked 550 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 $0.00550 $0.00550
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 6d ago against content hash 18e20d07157e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

orbit-agent-workbench 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 6d 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.

AGENTS.md · 33 lines

What it actually says

AgentForge Mission Control Instructions

Always read PROJECT_MEMORY.md before changing this project.

This workspace is named AgentForge-MissionControl. It is the future source workspace for the AgentHub-to-main-Agent pivot.

Public release repository:

  • Canonical public GitHub repo: https://github.com/gaowei90098-creator/orbit-agent-workbench.
  • Current product name: Orbit.
  • Use the workbench remote for the new public repo. The old origin / orbit remotes may still exist locally for historical reference and must not be treated as the release target.
  • Ignore local-only .claude/worktrees/, reference_repos/, node_modules/, out/, and dist/ when checking what has been published.
  • Before a new session changes code, compare against workbench/main or the latest PROJECT_MEMORY.md entry so the session does not resurrect older AgentHub/Orbit-Hub state.

This repository is being turned into a main Agent / Orchestrator product:

  • AgentHub receives a project goal.
  • The main Agent decomposes it into a task DAG.
  • Sub-agents receive bounded task contracts and execute.
  • Shared coordination state keeps task granularity, file scope, interface contracts, memory, and verification aligned.
  • Every coding session must append or update PROJECT_MEMORY.md with completed changes and the next recommended work.
  • After any source, runtime, UI, asset, config, packaging, or dependency change that affects the desktop app, rebuild and repackage the app before stopping. The user launches /Users/gao90098/Desktop/Orbit.app, so finishing at source edits only leaves them with a stale desktop build.
  • Required desktop delivery loop for app-affecting changes:
    1. Run the relevant validation commands, at minimum npm run typecheck; run npm test when behavior changed.
    2. Run npm run build.
    3. Run npm run unpack.
    4. Replace /Users/gao90098/Desktop/Orbit.app with dist/mac-arm64/Orbit.app.
    5. Ad-hoc sign the replaced app with codesign --force --deep --sign - /Users/gao90098/Desktop/Orbit.app.
    6. Verify with codesign --verify --deep --strict --verbose=2 /Users/gao90098/Desktop/Orbit.app.
    7. Relaunch or at least explicitly report whether relaunch/listener verification was completed.

Do not treat AgentHub as only a multi-model chat shell. Preserve the original goal: project intake -> decomposition -> collaboration -> verification -> synthesis.

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. 6d ago First seen · 33 lines · 550 tokens per session scan A 18e20d07157e

Subscribe to this mod's changes

orbit-agent-workbench AGENTS.md is an instructions file published in the GitHub repository gaowei90098-creator/orbit-agent-workbench (2 stars, last pushed 2mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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 2026-08-31.

Building agentsClaude CodeMemory and contextagent-orchestrationai-agentscodexelectron
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 · 5,182 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

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

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