Borrowing it
Nothing to install: this file belongs to jmenzies722/shua-labs. 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/jmenzies722/shua-labs/master/AGENTS.mdgit clone --depth 1 https://github.com/jmenzies722/shua-labsWrote 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/jmenzies722/shua-labs/agents-md)<a href="https://agentmods.dev/instructions/jmenzies722/shua-labs/agents-md"><img src="https://agentmods.dev/badge/instructions/jmenzies722/shua-labs/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/jmenzies722/shua-labs/agents-md"><img src="https://agentmods.dev/badge/instructions/jmenzies722/shua-labs/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 | $0.00471 | $0.00471 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
shua-labs 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.
What it actually says
Agents
How cloud agents work in this repo — the public lab surface for Shua Labs.
What Shua Labs is
An independent AI lab building software, systems, and companies in public. Not a single SaaS product. The website is the canonical public home; social distributes; GitHub proves.
Brand constraints
Read docs/BRAND.md before changing UI.
Hard rules:
- Light Notion-like monochrome (
#ffffff/#37352f), DM Sans / IBM Plex Mono — no chroma, no dark neon lab look - Soft panels and list rows; no background grids or glowing accents
- Content lives in
content/— do not scatter project data through JSX - Mark placeholders explicitly; empty is honest
Architecture
- App Router routes:
//work/build/build/[slug]/research/research/[slug]/about - Typed content:
content/{types,projects,build-log,research,social}.ts - Layout chrome:
components/layout/ - Homepage sections:
components/sections/ - Design tokens:
app/globals.css+tailwind.config.ts
Testing requirements
Before claiming done:
npm test
npm run typecheck
npm run lint
npm run build
Inspect every required route. Respect prefers-reduced-motion. Do not invent customers or live YouTube/Instagram URLs.
Bus
GitHub is the bus. Issues, PRs, and comments are the handoff channel.
Roles (Devon kit)
| Role | Does | Does not |
|---|---|---|
| Marcus | Writes specs | Write production code |
| Devon | Implements. Owns branch, tests, HANDOFF.md |
Deploy without founder ask |
| Ivy | Prod gate | Implement |
| Shua | Gates deploy. Owns live | — |
Production deploys from master → shua-labs.vercel.app. Founder-authorized merge ships.
After every job
Post on the PR / update HANDOFF.md:
- Outcome · Repo · Branch · Status · Tests · PR · Next
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 Changed · +5 tokens per session 064ba0399602
- 9d ago First seen · 61 lines · 466 tokens per session scan A f6f6a957fd32
shua-labs AGENTS.md is an instructions file published in the GitHub repository jmenzies722/shua-labs (2 stars, last pushed 6d ago), licensed MIT. It adds 471 tokens to every session, about $0.0024 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
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 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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.