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/vibeinging/yiyi/agents-mdgit clone --depth 1 https://github.com/vibeinging/YiYiWrote 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/vibeinging/yiyi/agents-md)<a href="https://agentmods.dev/instructions/vibeinging/yiyi/agents-md"><img src="https://agentmods.dev/badge/instructions/vibeinging/yiyi/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 | $0.04053 | $0.04053 |
| Opus 5 | $0.02027 | $0.02027 |
| Sonnet 5 | $0.00811 | $0.00811 |
| Haiku 4.5 | $0.00405 | $0.00405 |
Grade A, and why
YiYi 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 4d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Onboarding for coding AIs (Claude Code, Cursor, Codex, …) contributing to YiYi.
If you're a human reader, this also works as a fast tour — just skim §1 then jump to whatever section matches the task.
1. 30-second tour
YiYi is a desktop AI personal assistant — Tauri (Rust backend) + React 18 / TypeScript frontend. Single binary, runs locally on the user's machine. Data lives in SQLite (WAL mode) under ~/.yiyi/.
Differentiation vs. other open-source agents:
- Deeply tuned for DeepSeek V4 (Pro / Flash) — implicit prefix cache, 1M context, 120× hit/miss price gap drives most architectural choices.
- White-box co-construction — the agent never silently rewrites its own skills or rules. Anything it proposes (new skill, new principle) goes through an Inbox the user approves. See §6.
- Multi-platform bots out of the box — Discord, QQ, Telegram, DingTalk, Feishu, WeCom, Webhook.
Default behaviour expectations:
- Read code before editing. Keep changes scoped. No speculative abstractions.
- Don't break the prefix cache (see §7).
- Don't add features the user didn't ask for.
- Finish things; "能跑 ≠ 能用，能用 ≠ 好用".
2. Repo layout
/
├── AGENTS.md ← this file (you're here)
├── README.md ← public-facing intro / screenshots
├── app/
│ ├── src/ ← React frontend (Vite + TS + Tailwind)
│ │ ├── pages/ Chat, CronJobs, Bots, Skills, Settings, …
│ │ ├── components/
│ │ ├── api/ Tauri invoke wrappers
│ │ ├── stores/ Zustand stores
│ │ └── i18n.ts zh/en strings
│ └── src-tauri/ ← Rust backend (the heart of YiYi)
│ ├── src/
│ │ ├── lib.rs App init + plugin setup
│ │ ├── main.rs CLI dispatch (`yiyi doctor`, …) → lib.rs::run()
│ │ ├── doctor.rs Environment self-check
│ │ ├── tray.rs System tray menu
│ │ ├── commands/ Tauri command handlers
│ │ │ ├── agent/ chat / streaming / history
│ │ │ ├── bots.rs / cronjobs.rs / skills.rs / workspace.rs / …
│ │ ├── engine/ ← Core domain logic
│ │ │ ├── react_agent/
│ │ │ │ ├── core.rs Think → Act → Observe loop
│ │ │ │ ├── prompt.rs System prompt + persona prefix
│ │ │ │ ├── compaction.rs Long-context handling
│ │ │ │ ├── growth.rs Skill / principle proposals → Inbox
│ │ │ │ └── loop_guard.rs Anti-loop guard per turn
│ │ │ ├── tools/ ← Tool dispatch (heavy file, expect 3k+ LOC)
│ │ │ │ ├── file_tools.rs read/write/edit/append/delete + undo_edit
│ │ │ │ ├── shell_security.rs Two-layer regex (Hardline ▸ Block ▸ Warn)
│ │ │ │ ├── output_envelope.rs Trust + MultimodalEnvelope
│ │ │ │ ├── permission_gate.rs Native OS approval dialog
│ │ │ │ └── …
│ │ │ ├── llm_client/ OpenAI / Anthropic / Google formats
│ │ │ ├── bots/ Per-platform adapters + BotManager
│ │ │ ├── infra/ mcp_runtime, dep_check, python_bridge
│ │ │ ├── db/ SQLite schema + queries
│ │ │ ├── checkpoint.rs Shadow-git per-turn snapshots
│ │ │ ├── scheduler.rs Cron / delay / once jobs
│ │ │ ├── prompt_cache.rs FNV fingerprint + cache-break detect
│ │ │ └── tool_registry_global.rs Single source of truth for tools
│ │ ├── state/ AppState, Config
│ │ └── test_support/ Test helpers (feature-gated)
│ ├── tests/ ← Integration tests (flat layout, one file per area)
│ └── Cargo.toml
└── evals/ ← Behaviour eval YAML cases + rubric
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.
- 4d ago First seen · 255 lines · 4,053 tokens per session scan A ec32b805221f
YiYi AGENTS.md is an instructions file published in the GitHub repository vibeinging/YiYi (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 4,053 tokens to every session, about $0.0203 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 2026-08-30.
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.