aiworkspace AGENTS.md

aiworkspace AGENTS.md is an instructions file for Codex, OpenCode from a-tokyo/aiworkspace. It costs 388 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for Aiworkspace, a central project that manages shared AI configuration, skills, scripts, and tools across multiple repositories.

In plain words
What is it for?
It helps developers manage workspace-wide or project-only skills, mirror configuration, regenerate tool integrations, and maintain the automation scripts.
Why use it?
It explains where shared configuration lives and which commands install, remove, create, synchronize, or update skills, reducing mistakes in workspace setup.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/a-tokyo/aiworkspace/agents-md
Clone the repo
git clone --depth 1 https://github.com/a-tokyo/aiworkspace

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 aiworkspace AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/a-tokyo/aiworkspace/agents-md.svg)](https://agentmods.dev/instructions/a-tokyo/aiworkspace/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/a-tokyo/aiworkspace/agents-md"><img src="https://agentmods.dev/badge/instructions/a-tokyo/aiworkspace/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 388 This file is loaded in full into every session.
When invoked 388 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00388 $0.00388
Opus 5 $0.00194 $0.00194
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 5d ago against content hash 8b437174212c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aiworkspace 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 5d 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 · 35 lines

What it actually says

AI Workspace

This is the workspace/ repo — central hub for shared AI config in a multi-repo workspace.

Structure

  • workspace/root-config/ — Canonical source for root-level AI configs (AGENTS.md, workspace-wide skills, tool dirs). See workspace/root-config/README.md.
  • workspace/scripts/ — Automation: setup, hooks, skill wrappers.
  • workspace/.agents/skills/ — Workspace project-specific skills (available only within this repo).

Key Commands

Command What it does
npm run skills:setup Mirror root-config to parent root, create skill symlinks
npm run skills:add -- <source> Install a skill (workspace-wide)
npm run skills:add -- <source> --project <repo> Install a skill (project-only)
npm run skills:remove Remove a skill
npm run skills:create -- --name <name> Create a manual skill scaffold
npm run sync Regenerate MCP twins and mirror root-config to parent root
npm run upgrade Pull latest scripts from upstream

Conventions

  • Edit workspace/root-config/AGENTS.md, not the root copy (it gets overwritten on sync).
  • Skills in workspace/root-config/.agents/skills/ are workspace-wide (shared with all projects).
  • Skills in workspace/.agents/skills/ are specific to this repo.
  • Use --project <repo> to install skills into a specific project.
  • The setup script is generic: adding configs to workspace/root-config/ requires no script changes.
  • postinstall restores skills from lock, runs setup, installs git hooks.

Code Quality

  • Config precedence: always use the nearest config file to the code you are changing.
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. 5d ago First seen · 35 lines · 388 tokens per session scan A 8b437174212c

Subscribe to this mod's changes

aiworkspace AGENTS.md is an instructions file published in the GitHub repository a-tokyo/aiworkspace (19 stars, last pushed 17d ago), licensed Apache-2.0. It adds 388 tokens to every session, about $0.0019 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 2026-08-30.