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.
npx agentmods add instructions/grojof/ai-workspace-generator/agents-mdgit clone --depth 1 https://github.com/grojof/ai-workspace-generatorWrote 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/grojof/ai-workspace-generator/agents-md)<a href="https://agentmods.dev/instructions/grojof/ai-workspace-generator/agents-md"><img src="https://agentmods.dev/badge/instructions/grojof/ai-workspace-generator/agents-md.svg" alt="Measured on agentmods" 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 | $0.05797 | $0.05797 |
| Opus 5 | $0.02899 | $0.02899 |
| Sonnet 5 | $0.01159 | $0.01159 |
| Haiku 4.5 | $0.00580 | $0.00580 |
Grade A, and why
ai-workspace-generator 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.
How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-workspace-generator — AI Agent Guide (AGENTS.md)
Node/TypeScript CLI that scaffolds and adapts AI workspaces (Claude Code + Copilot) from one config.
This file is the single source of truth for AI agents (Claude Code, GitHub Copilot, Cursor…).
Tool-specific files (CLAUDE.md, .github/copilot-instructions.md) are generated adapters that
mirror or import this content — edit rules here, then run ai-workspace sync.
Sections between ai-workspace:begin/end markers are generated. Add your own notes outside them;
they survive regeneration.
Universal conventions (Layer 0)
These apply to every contributor and every file, regardless of language.
Encoding & line endings
- Files are UTF-8, no BOM. Newlines are LF. Final newline at EOF.
.editorconfigand.gitattributesenforce this — do not fight them.
Commits
- Conventional Commits in the imperative mood:
feat:,fix:,refactor:,docs:,test:,chore:. - Subject ≤ 72 chars, present tense ("add", not "added"). Explain the why in the body.
- One logical change per commit. Do not mix refactors with behavior changes.
Code style
- Match the surrounding code: naming, structure, comment density, idioms.
- Names are descriptive and in English. No abbreviations that aren't standard.
- Keep functions small and single-purpose. Prefer early returns over deep nesting.
- No dead code, no commented-out blocks, no leftover debug logging.
Reviews & safety
- Never commit secrets. Never weaken auth, validation, or escaping to "make it work".
- Validate inputs at boundaries. Handle errors explicitly — no silent catches.
- Changes that are hard to reverse or outward-facing need explicit confirmation.
Token efficiency (how agents should work here)
- Reference, don't duplicate. Link to skills/docs instead of restating them.
- Load detail on demand: read scoped instructions/skills only when relevant.
- Prefer the living docs (
docs/development/status/PROJECT-STATE.md) over re-scanning the whole repo. - Use context7 (MCP) for up-to-date, version-pinned library docs instead of guessing.
- Offer, don't dump. When extra explanation is optional, offer "say X and I'll explain X" instead of long unsolicited detail.
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.
- 5d ago First seen · 360 lines · 5,797 tokens per session scan A f96c4f279fd0
ai-workspace-generator AGENTS.md is an instructions file published in the GitHub repository grojof/ai-workspace-generator (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,797 tokens to every session, about $0.0290 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
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.