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/ntygod/zhiwei/agents-mdgit clone --depth 1 https://github.com/ntygod/ZhiWeiWrote 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/ntygod/zhiwei/agents-md)<a href="https://agentmods.dev/instructions/ntygod/zhiwei/agents-md"><img src="https://agentmods.dev/badge/instructions/ntygod/zhiwei/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 | $0.01019 | $0.01019 |
| Opus 5 | $0.00509 | $0.00509 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
ZhiWei 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository contains a Spring Boot backend and a Vue frontend. Backend code lives in src/main/java/com/lifepilot, split by domains such as agent, interaction, memory, workflow, mcp, and knowledge. Runtime config, Flyway SQL, built-in workflows, prompts, and skills are under src/main/resources. Backend tests live in src/test/java and src/test/resources.
The frontend lives in zhiwei-web/. Put route pages in src/views, reusable UI in src/components, Pinia stores in src/stores, composables in src/composables, and API clients in src/api. Docs live in docs/.
Agent Harness
This repo uses the AI Coding Harness pattern. Keep this file as the short entry point; reusable harness concepts live under docs/harness/core/, while this repository's adapter lives under docs/harness/adapters/zhiwei/.
- Canonical project skills live in
.agents/skills/. - Codex-discoverable skill wrappers live in
.codex/skills/. - Claude Code compatibility assets remain in
.claude/. - When working on Java, frontend, Flyway, or Tauri files, read
docs/harness/adapters/zhiwei/rules.mdand the matching rule file before editing. - Before delivery, follow
docs/harness/adapters/zhiwei/quality-gates.mdor theshipskill.
Build, Test, and Development Commands
Backend: mvn spring-boot:run starts the backend, mvn compile verifies cross-module compilation, mvn test runs JUnit/jqwik tests, and mvn clean package -DskipTests builds target/zhiwei.jar.
Frontend: cd zhiwei-web && npm install, then npm run dev for Vite, npm run build for production assets, npm run test:run for Vitest, and npm run lint for ESLint. docker compose up -d starts the integrated stack from .env.
Coding Style & Naming Conventions
Java uses 4-space indentation, lowercase packages, and PascalCase types. Prefer Java 22 features used here: record, sealed interface, pattern matching, and virtual threads where appropriate. Business-tunable values belong in @ConfigurationProperties and application.yml, not hardcoded constants.
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 · 39 lines · 1,019 tokens per session scan A 227a8c33abda
ZhiWei AGENTS.md is an instructions file published in the GitHub repository ntygod/ZhiWei (137 stars, last pushed 24d ago), licensed MIT. It adds 1,019 tokens to every session, about $0.0051 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
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.
claude-memory-mcp AGENTS.md
Instructions for WhenMoon-afk/claude-memory-mcp, covering mooncite repository contract, product boundary, fixed architecture, sources of truth and change discipline.
doltlite AGENTS.md
AGENTS.md instructions for dolthub/doltlite, covering agents.md, project nature, licensing and file headers, comments: minimal by default and build.
LexiconLocal CLAUDE.md
Claude Code instructions for alexeymohr/LexiconLocal, covering lexiconlocal, read first, this repository is public. the operator's data is not, tech stack (fixed — do not substitute) and hard rules.
agent-kudos AGENTS.md
AGENTS.md instructions for Coaden/agent-kudos, covering agents.md, working agreement, architectural invariants and quality gates.
codex-agent-mem AGENTS.md
Instructions for MarceloCaporale/codex-agent-mem, covering agents, public name vs import name, what this project is, working rules for agents and fastest commands.