youclaw AGENTS.md

Repository instructions for a Bun backend and React/Vite frontend, including where modules, tests, agent definitions, and runtime data are stored.

In plain words
What is it for?
Use them to start the backend or web app, run tests and type checks, lint or build the frontend, and place new code in the correct module.
Why use it?
They make the project structure, development commands, coding style, and testing expectations clear to an agent.

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/ottermind/youclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/OtterMind/youclaw

Made for: Codex, OpenCode.

Per session 783 This file is loaded in full into every session.
When invoked 783 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 $0.00783 $0.00783
Opus 5 $0.00392 $0.00392
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 2d ago against content hash 430074d6f251, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

youclaw 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 · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

The Bun backend lives in src/, organized by domain: agent/, channel/, db/, routes/, scheduler/, memory/, and skills/. End-to-end and database-heavy tests live in tests/, with occasional colocated tests such as src/agent/manager.test.ts. The React/Vite frontend lives in web/src/; static assets are in web/public/ and web/src/assets/. Runtime data is stored under data/, while agent definitions live in agents/<agent-id>/.

Build, Test, and Development Commands

Use Bun for both workspaces.

  • bun run dev: start the backend with hot reload on port PORT (default 62601).
  • bun run start: run the backend without hot reload.
  • bun run dev:web: start the frontend dev server from web/.
  • bun test: run the Bun test suite.
  • bun run typecheck: run root TypeScript checks.
  • cd web && bun run lint: lint the frontend with ESLint.
  • cd web && bun run build: type-check and build the frontend bundle.

Coding Style & Naming Conventions

Write TypeScript with 2-space indentation, single quotes, and no semicolons; match nearby files when in doubt. Keep backend modules small and domain-focused. Use PascalCase for React components/pages (Tasks.tsx), camelCase for functions/hooks (useChat.ts), and descriptive directory names (src/routes, web/src/components/ui). Frontend lint rules are defined in web/eslint.config.js; no Prettier config is checked in, so avoid formatting-only churn.

Testing Guidelines

Tests use bun:test. Name files *.test.ts and prefer colocated tests for tight unit coverage or tests/ for integration scenarios. Reuse tests/setup.ts for shared env and SQLite setup. No coverage threshold is enforced today; add regression tests for any route, scheduler, DB, or i18n behavior you change.

Read the full file on GitHub · 28 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 · 28 lines · 783 tokens per session scan A 430074d6f251

Subscribe to this mod's changes

youclaw AGENTS.md is an instructions file published in the GitHub repository OtterMind/youclaw (724 stars, last pushed 4mo ago), licensed MIT. It adds 783 tokens to every session, about $0.0039 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.