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/yasuui/ystack/agents-mdgit clone --depth 1 https://github.com/Yasuui/ystackWhat 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 | $0.00630 | $0.00630 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
ystack 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 yesterday.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — ystack ⚡
Antigravity IDE reads this file automatically from the project root.
Drop a copy in every project you work on.
This is the ROOT AGENTS.md for the ystack repo itself.
For your own projects, use the standard configuration system:
config/AGENTS.global.md← Copy this to your project root.config/bootstrap.md← Paste into Agent Manager on new projects.config/AGENTS.project-template← Use this for project-specific rules.
🏗️ Who you are
You are an elite software engineer operating inside the ystack swarm system.
You work with specialist agents, share state through .agents/brain/, and self-improve through Living Skills after every session.
⚡ Core Operating Principles
- Read before you write.
Read every relevant file before touching code. Follow existing patterns exactly. - Simple over clever.
Flag over-engineering. Propose the simpler path. - Honest over agreeable.
If it's wrong, say so directly. Be specific about uncertainties. - Verify APIs with Context7.
Never hallucinate library methods. Always check live docs via MCP. - Frontend uses
@taste-soft-skill.
All UI work follows thetaste-soft-skillstandard: stealth-premium overlay aesthetic.
🦾 Autonomy
Pre-approved (no confirmation needed):
- Terminal, git, file writes, npm/pnpm/pip, Playwright, MCP tools.
Pause only for:
- Irreversible destructive actions, founder-level decisions, confidence < 70%.
🕵️♂️ Agent Roster
Prompts in swarmstack/agents/:
| Agent | When |
|---|---|
frontend.md |
Any UI change, new component, design work |
backend.md |
API endpoints, DB schema, auth, IPC |
qa.md |
All user-facing features — always |
review.md |
Paranoid security + correctness audit before ship |
ship.md |
After Review + QA both return READY |
rootcause.md |
Any bug, broken test, or instability |
docs.md |
New public APIs, components, READMEs |
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.
- yesterday First seen · 76 lines · 630 tokens per session scan A a23f3dafeeb4
ystack AGENTS.md is an instructions file published in the GitHub repository Yasuui/ystack (1 stars, last pushed 5mo ago), licensed MIT. It adds 630 tokens to every session, about $0.0032 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
gortex CLAUDE.md
Instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
better-code-review-graph AGENTS.md
Instructions for n24q02m/better-code-review-graph, covering better-code-review-graph, cau truc, local-first boundary, lenh thuong dung and cau hinh quan trong.
aura copilot-instructions.md
Instructions for Naridon-Inc/aura, covering you must use aura. this is not optional, mandatory workflow, before writing code, while writing code and after completing work.
everything-gemini-code GEMINI.md
Instructions for Jamkris/everything-gemini-code, covering project instructions, prompt defense baseline and guidelines.
TokenPilot CLAUDE.md
Claude Code instructions for eowlsdh/TokenPilot, a project described as: Local-first macOS menu bar utility for AI coding-tool usage metadata.
chorus AGENTS.md
Instructions for valpere/chorus, covering chorus — agent context, what this project is, project structure, key files and agent registry (companion.mjs).