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/luohy15/y-agent/agents-mdgit clone --depth 1 https://github.com/luohy15/y-agentWhat 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 | $0.08023 | $0.08023 |
| Opus 5 | $0.04012 | $0.04012 |
| Sonnet 5 | $0.01605 | $0.01605 |
| Haiku 4.5 | $0.00802 | $0.00802 |
Grade A, and why
y-agent 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 2d 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
y-agent
Personal AI agent platform: React web UI + FastAPI backend + async worker, deployed as AWS Lambda (SAM). Runs Claude Code subprocesses remotely on EC2 over SSH, with a Telegram bot surface and cross-skill orchestration via trace context.
Architecture
Web (React) ─┐ ┌─→ Claude Code subprocess (EC2, SSH)
Telegram Bot ─┼─→ API (FastAPI/Lambda) → SQS → Worker (Lambda) ─┤
CLI (y) ─┘ └─→ Post-hooks (trace, telegram, todo)
Storage (SQLAlchemy / PostgreSQL) is shared by API / Worker / CLI / admin.
Packages
UV workspace with Python members + one React frontend:
| Package | Purpose | Entry |
|---|---|---|
| storage | ORM models, repos, services, DTOs, celery config, global config loader | src/storage/ |
| agent | Claude Code runner, SSH/EC2 pool, tool shims, skills discovery | src/agent/claude_code.py, src/agent/detach.py |
| api | FastAPI REST + SSE, JWT auth, controllers for each feature | src/api/app.py (port 8001) |
| worker | Celery/SQS task consumer, runs agent subprocesses, post-hooks, RSS pipeline | src/worker/runner.py |
| cli | Click CLI (y command), all feature subcommands |
src/yagent/command_option.py |
| admin | Lambda handler for DB init + scheduled jobs (reminders, RSS) | handler.py |
| web | React 19 + Vite + TailwindCSS SPA | src/main.tsx (port 5174) |
Other top-level dirs: scripts/ (deploy, DNS, IAM), template.yaml / samconfig.toml
(SAM), worktree/post-create.sh (symlink shared files into new dev worktrees).
Tech Stack
- Python 3.11+, UV workspace, Hatchling build
- FastAPI + Uvicorn + SSE (sse-starlette) + Lambda Web Adapter (response streaming)
- SQLAlchemy 2.0 + PostgreSQL (psycopg v3), DynamoDB (per-process lease cache)
- Celery 5.3 (filesystem broker local, SQS in prod)
- React 19 + React Router 7 + Vite 7 + TailwindCSS 4 + SWR
- AWS SAM: Lambda (API / Worker / Admin), SQS, S3 + CloudFront (web + link/RSS content), EventBridge schedules (reminders, RSS), DynamoDB
- Integrations: Telegram Bot API, Google OAuth, SSH/Paramiko, EC2 lifecycle (boto3), oxylabs (WeChat / generic pages), yt-dlp (YouTube), Jina AI reader (Twitter/X)
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.
- 2d ago First seen · 489 lines · 8,023 tokens per session scan A 58de8705a926
y-agent AGENTS.md is an instructions file published in the GitHub repository luohy15/y-agent (219 stars, last pushed 2d ago), licensed MIT. It adds 8,023 tokens to every session, about $0.0401 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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.