agent-workspace AGENTS.md

Repository instructions for a TypeScript package called agent-workspace. They explain its folders, coding rules, commands, tests, and how it generates files for coding agents.

In plain words
What is it for?
Use them when analyzing, changing, testing, or extending agent-workspace. They cover commands such as type checking, running tests, and using the command-line interface.
Why use it?
They give an agent one reference for working in the repository without guessing its structure or development process. They also clarify that the project is a single package, not a monorepo, which is a repository containing multiple related packages.

Instructions file for CodexOpenCode

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/viethann/agent-workspace/agents-md
Clone the repo
git clone --depth 1 https://github.com/VietHann/agent-workspace

Made for: Codex, OpenCode.

Per session 493 This file is loaded in full into every session.
When invoked 493 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.

ModelPer sessionOnce invoked
Fable 5 $0.00493 $0.00493
Opus 5 $0.00246 $0.00246
Sonnet 5 $0.00099 $0.00099
Haiku 4.5 $0.00049 $0.00049

Measured 2d ago against content hash dd09d9837978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-workspace 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.

AGENTS.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

This is a single TypeScript package, not a monorepo. src/analyzer/ collects repository evidence into ProjectContext; src/catalog/ loads and validates repository-owned YAML; src/generator.ts creates canonical files and owns safe writes; and src/adapters/ translates the manifest into vendor entry points without writing directly. src/commands.ts exposes reusable command operations, while src/cli.ts contains terminal presentation.

Built-in definitions live in agents/*.yaml and skills/<name>/skill.yaml. Keep these as data rather than embedding their content in TypeScript. templates/ is the contribution starting surface. examples/next-supabase/ is both a representative fixture and a checked-in generated workspace. Tests in tests/ cover schemas, analysis, generation, and real CLI execution.

Build, Test, and Development Commands

  • pnpm dev -- <command> runs the source CLI, for example pnpm dev -- analyze ..
  • pnpm typecheck runs strict TypeScript checking without emitting files.
  • pnpm test runs all Vitest tests once.
  • pnpm vitest run tests/analyzer.test.ts runs one test file.
  • pnpm validate validates catalog schemas, type-checks, and runs tests.
  • pnpm build bundles ESM executables and declarations into dist/ with tsup.

Coding Style & Naming Conventions

TypeScript uses strict mode, NodeNext modules, two-space indentation, and explicit .js suffixes in source imports. Extension names and workflow IDs are lowercase kebab-case; extension versions are semantic versions. Zod schemas are strict, so public format changes require deliberate schema and fixture updates. Preserve deterministic sorting in analysis and generation. All writes must remain inside the target repository and must preserve conflicts unless the caller selects force.

Testing Guidelines

Vitest runs in the Node environment. Use temporary directories from tests/helpers.ts for filesystem behavior and clean them after each test. Test both observable files and parsed schemas. CLI behavior changes require a child-process test, not only direct function coverage.

Read the full file on GitHub · 29 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.

  1. 2d ago First seen · 29 lines · 493 tokens per session scan A dd09d9837978

Subscribe to this mod's changes

agent-workspace AGENTS.md is an instructions file published in the GitHub repository VietHann/agent-workspace (4 stars, last pushed 2d ago), licensed MIT. It adds 493 tokens to every session, about $0.0025 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.