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/h0x91b/dev-3.0/agents-mdgit clone --depth 1 https://github.com/h0x91b/dev-3.0What 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 | $0.13738 | $0.13738 |
| Opus 5 | $0.06869 | $0.06869 |
| Sonnet 5 | $0.02748 | $0.02748 |
| Haiku 4.5 | $0.01374 | $0.01374 |
Grade A, and why
dev-3.0 AGENTS.md scanned grade A with 1 finding 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 3d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**NEVER use `Bun.spawn`/`Bun.spawnSync` directly** — always import `spawn`/`spawnSync` from `src/bun/spawn.ts`. macOS `.app` bundles inherit a minimal PATH; we patch `process.env.PATH` at startup (`shell-env.ts` → `index How it starts
The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
Note:
CLAUDE.mdis a symlink to this file (AGENTS.md) so all agents (Claude Code, Cursor, Codex, …) read the same instructions. Both files appearing changed in a diff is expected.
Response style
This repo does not impose one. Shape, language and register of your replies belong to your harness's output style and the user's own instructions. The English-only rule applies solely to text written into the repo (see Language policy), never to replies.
What is this
A terminal-centric project manager — iTerm2 meets Kanban. Desktop app for managing multiple AI coding agents and terminal tools across tasks and projects. Built with Electrobun (not Electron), React 19, Tailwind CSS, Vite; runtime is Bun. Supports macOS, Linux, and Windows — Windows support is brand new and may still be rough (it ships with every release, unsigned at this time).
Key idea: each project is a git repo; each task gets its own git worktree + terminal running inside tmux with a preconfigured command (e.g., claude).
- Full product concept + implementation status tracker:
concept.md - Design system (colors, typography, components, glass morphism, themes):
DESIGN.md— follow it for any UI code - UX architecture manifest (object model, navigation, surfaces, action taxonomy, placement rules, complexity budgets):
docs/ux/PRODUCT_UX_BIBLE.md+ machine-readabledocs/ux/ux-architecture.yaml— the canonical UX reference for where features live and which surface owns which action
UI/UX work — which skill, and when (MANDATORY)
Two different jobs, two different skills, and they are not interchangeable. /ux-principal decides where a thing goes, before it exists. The better-* family judges how it is built. Pick by what the change does, not by how big it is:
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.
- 3d ago First seen · 477 lines · 13,738 tokens per session scan A 23bc95f45c64
dev-3.0 AGENTS.md is an instructions file published in the GitHub repository h0x91b/dev-3.0 (248 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13,738 tokens to every session, about $0.0687 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
opencode-swarm copilot-instructions.md
Instructions for ZaxbyHub/opencode-swarm, covering mandatory pr publication protocol, pr title requirements, pr body requirements, validation requirements and release fragment requirement.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
metis AGENTS.md
Instructions for Wholiver/metis, covering agent development guide, objective, start every task, repository map and desktop frontend changes (mandatory).
crewplane AGENTS.md
Instructions for crewplaneai/crewplane, covering agents.md, repo facts, read first, repo map and project heuristics.
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
AgentsMesh CLAUDE.md
Claude Code instructions for AgentsMesh/AgentsMesh, covering claude.md, project overview, components, development environment and quick start.