What is learn-opencode-agent AGENTS.md?

Repository instructions that tell a coding agent how to work in the qqzhangyanhua/learn-opencode-agent project, including which documentation to read, how to make changes, and how to run checks.

Use them when modifying this VitePress book site to locate relevant documentation, follow the expected workflow, run validation scripts, and report changes and remaining risks.

They give the agent the project’s local rules and reduce the risk of editing the wrong files, skipping tests, or making high-risk changes without review.

learn-opencode-agent AGENTS.md — Instructions file for Codex and OpenCode by qqzhangyanhua: Repository instructions that tell a coding agent

Install

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.

agentmods

npx agentmods add instructions/qqzhangyanhua/learn-opencode-agent/agents-md

Clone the repo

git clone --depth 1 https://github.com/qqzhangyanhua/learn-opencode-agent

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/qqzhangyanhua/learn-opencode-agent/agents-md.svg)](https://agentmods.dev/instructions/qqzhangyanhua/learn-opencode-agent/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/qqzhangyanhua/learn-opencode-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/qqzhangyanhua/learn-opencode-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 864 This file is loaded in full into every session.

When invoked 864 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00864	$0.00864
Opus 5	$0.00432	$0.00432
Sonnet 5	$0.00173	$0.00173
Haiku 4.5	$0.00086	$0.00086

Measured 4d ago against content hash 93ead1b9dbf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-opencode-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 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.

AGENTS.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Read First

docs/project-map.md
docs/testing.md
docs/dangerous-areas.md
docs/debugging.md
.context/prefs/coding-style.md
.context/prefs/workflow.md

Default Agent Workflow

Understand the task and check current workspace state.
Search for relevant files before editing.
Make the smallest safe change.
Add or update tests/checks when behavior changes.
Run ./scripts/check.sh or the narrower verified command listed in docs/testing.md.
Report changed files, validation results, and remaining risks.

Do Not

Edit generated files directly.
Modify secrets or local environment files.
Change deployment, infrastructure, permissions, public API examples, navigation contracts, or generated/cache artifacts without calling out the risk.
Hide failing or skipped checks.

Large or High-Risk Changes

Use docs/agent-plan-template.md before editing. Stop after the plan for high-risk areas and ask for human review.

Project Structure & Module Organization

This repository is a VitePress-based book site. Main content lives in docs/, with chapter folders such as docs/01-agent-basics/, practice lessons in docs/practice/, and intermediate chapters in docs/intermediate/. Interactive source examples live in practice/ as runnable TypeScript entry files like p01-minimal-agent.ts. Theme code and UI components live under .vitepress/, especially .vitepress/theme/components/ and .vitepress/theme/data/. Validation and release checks are script-driven from scripts/check-*.mjs.

Build, Test, and Development Commands

bun install: install dependencies.
bun run dev: start the local VitePress dev server.
bun run build: build the static site.
bun run preview: preview the built site locally.
bun run typecheck: run TypeScript checks for .vitepress/.
bun run check:content: validate document structure and required metadata.
bun run check:practice: verify practice entry pages.
bun run build:strict: run the full validation pipeline before release.

Read the full file on GitHub · 72 lines

Changes

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 · 72 lines · 864 tokens per session scan A 93ead1b9dbf3

Subscribe to this mod's changes

learn-opencode-agent AGENTS.md is an instructions file published in the GitHub repository qqzhangyanhua/learn-opencode-agent (168 stars, last pushed 21d ago), licensed MIT. It adds 864 tokens to every session, about $0.0043 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.

Building agents agentic-workflow ai-agents ai-coding-agent context-engineering opencode

intent-driven-template AGENTS.md

Instructions for intent-driven-dev/intent-driven-template, a project described as: OpenSpec and OpenCode template for intent-driven development with specs, ADRs, C4 diagrams, Gherkin, TDD, Multi-Model Adversarial Spec Authoring, Glossary for Domain Terms, and reusable engineering workflows. This also makes OpenSpec…

intent-driven-dev/intent-driven-template · 42 tokens

shopify-app-builder GEMINI.md

Gemini CLI instructions for khadinakbarlabs/shopify-app-builder: Use this extension for Shopify app architecture, implementation, debugging, launch readiness, and growth work.

khadinakbarlabs/shopify-app-builder · 176 tokens

claude-code-kickstart CLAUDE.md

Instructions for codeverbojan/claude-code-kickstart, covering 1. session protocol, 2. planning, 3. code quality, 4. execution loop and 5. verification.

codeverbojan/claude-code-kickstart · 1,335 tokens

Formic CLAUDE.md

Instructions for rickywo/Formic, covering formic task manager assistant, your capabilities, what you can do, what you cannot do and core behavioral rules.

rickywo/Formic · 6,475 tokens

odin-reflector CLAUDE.md

Instructions for OutlineDriven/odin-reflector, a project described as: Codex CLI meta-reflection layer for Outline-Driven Development. Add-on for the Claude plugin.

OutlineDriven/odin-reflector · 3 tokens

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).

microsoft/vscode · 6,785 tokens