What is argue AGENTS.md?

Repository instructions for the Argue project, which is a monorepo: one repository containing several related software packages. It explains the project layout, development commands, and package rules.

It helps with setup, development, type checking, tests, builds, linting, formatting, and release checks.

It gives coding agents the local rules needed to make compatible changes across the library, command-line tool, and web viewer.

argue AGENTS.md — Instructions file by onevcat

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/onevcat/argue/agents-md

Clone the repo

git clone --depth 1 https://github.com/onevcat/argue

Made for: Codex, OpenCode.

Per session 1,446 This file is loaded in full into every session.

When invoked 1,446 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	$0.01446	$0.01446
Opus 5	$0.00723	$0.00723
Sonnet 5	$0.00289	$0.00289
Haiku 4.5	$0.00145	$0.00145

Measured 2d ago against content hash 72501e7564bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

argue 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 · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Scope

This file applies to the whole argue repository.

Repo Overview

This repository is a monorepo with three workspace packages under unified versioning — root package.json holds the canonical version and every package carries the same number:

@onevcat/argue: reusable library (published)
@onevcat/argue-cli: CLI host (published)
@onevcat/argue-viewer: result viewer web app (private, private: true, never published)

The CLI depends on the library through a real semver dependency in packages/argue-cli/package.json. The viewer also consumes @onevcat/argue through a real semver range so its local build graph matches published reality.

Local Development

Use normal monorepo development flow for day-to-day work:

npm install
npm run dev

Useful commands:

npm run check: workspace typecheck
npm run test: workspace tests
npm run build: workspace build
npm run ci: check + test + build
npm run smoke:pack: tarball install smoke tests for both packages
npm run release:check: ci + smoke:pack
npm run lint: ESLint across repo
npm run format:check: Prettier validation
npm run format: format repo

Viewer-only shortcuts (for frontend iteration without rebuilding the library/CLI):

npm run dev:viewer: start the viewer Vite dev server
npm run build:viewer: build the viewer only
npm run check:viewer: typecheck the viewer only
npm run test:viewer: run the viewer test suite only

Recommended daily loop:

npm install
make code changes
npm run test
npm run release:check before merging changes that affect packaging, dependency shape, or CLI installability

Package Development Rules

All workspace packages share one version. Do not bump packages individually — every release bumps root + every packages/*/package.json together and @onevcat/argue-cli / @onevcat/argue-viewer always depend on the exact same @onevcat/argue version.

Workflow for any change that will be released:

Read the full file on GitHub · 154 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.

2d ago First seen · 154 lines · 1,446 tokens per session scan A 72501e7564bc

Subscribe to this mod's changes

argue AGENTS.md is an instructions file published in the GitHub repository onevcat/argue (273 stars, last pushed 1mo ago), licensed MIT. It adds 1,446 tokens to every session, about $0.0072 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.

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.

github/spec-kit · 7,104 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

argue AGENTS.md