Borrowing it
Nothing to install: this file belongs to tym83-ai/ai-workspace-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tym83-ai/ai-workspace-system/main/AGENTS.mdgit clone --depth 1 https://github.com/tym83-ai/ai-workspace-systemWrote 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.
[](https://agentmods.dev/instructions/tym83-ai/ai-workspace-system/agents-md)<a href="https://agentmods.dev/instructions/tym83-ai/ai-workspace-system/agents-md"><img src="https://agentmods.dev/badge/instructions/tym83-ai/ai-workspace-system/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.
<a href="https://agentmods.dev/instructions/tym83-ai/ai-workspace-system/agents-md"><img src="https://agentmods.dev/badge/instructions/tym83-ai/ai-workspace-system/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00388 | $0.00388 |
| Opus 5.5 | $0.00155 | $0.00155 |
| Sonnet 5.5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
ai-workspace-system 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 2mo 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.
What it actually says
AI Workspace System Agent Notes
This repository owns the local project launcher, sync workflow, bootstrap prompts, and shared AI workspace conventions.
Goals
- Keep local projects discoverable from configured project roots.
- Support both Codex and Claude Code without duplicating instructions.
- Keep automatic sync safe by default.
- Keep reusable prompts, scripts, and docs versioned without machine-specific values.
Safety Rules
- Do not put credentials, auth files, sessions, logs, sqlite state, or raw conversation history into Git.
- Do not make scheduled sync auto-commit by default.
- Do not force-push.
- Do not change existing project remotes silently.
- For mirror/upstream repos, preserve upstream remotes and add organization remotes explicitly.
- Do not hardcode a maintainer's home path, GitHub organization, project names, or private helper scripts in this repository.
Configuration Rules
- Local machine config lives in
~/.config/ai-workspace/config. config/config.examplemust stay generic and safe to publish.- Use
workspace-configureto collect machine-specific values interactively. - Keep generated logs under
$XDG_STATE_HOMEor~/.local/state, not inside this repository.
Instruction Conventions
AGENTS.mdis the canonical shared project instruction file.CLAUDE.mdshould import@AGENTS.mdand add Claude-specific notes only when needed.- Global Codex guidance lives in
~/.codex/AGENTS.md. - Global Claude guidance lives in
~/.claude/CLAUDE.mdand optional~/.claude/rules/.
Verification
- Run
bash -n bin/*after editing shell scripts. - Run
workspace-sync --dry-runafter changing sync logic. - Search for personal values before publishing.
- Keep docs and templates aligned with script behavior.
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.
- 2mo ago First seen · 41 lines · 388 tokens per session scan A 0ad6645218f2
ai-workspace-system AGENTS.md is an instructions file published in the GitHub repository tym83-ai/ai-workspace-system (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 388 tokens to every session, about $0.0016 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 2026-08-31.
ai-workspace-system AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-workspace-system AGENTS.mdtym83-ai/ai-workspace-system | Instructions file | 3 | 5mo ago | Apache-2.0 | A | 388 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |