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/hueyexe/opencode-ensemble/agents-mdgit clone --depth 1 https://github.com/hueyexe/opencode-ensembleWhat 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 | $0.04577 | $0.04577 |
| Opus 5 | $0.02289 | $0.02289 |
| Sonnet 5 | $0.00915 | $0.00915 |
| Haiku 4.5 | $0.00458 | $0.00458 |
Grade A, and why
opencode-ensemble 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opencode-ensemble — Agent Guidelines
What This Is
opencode-ensemble is an OpenCode plugin that enables agent teams: multiple agents running in parallel with peer-to-peer communication, shared task management, and coordinated execution. Built entirely on the public OpenCode plugin SDK (@opencode-ai/plugin) with zero internal dependencies.
Design Context
Users
OpenCode Ensemble is for developers using OpenCode to coordinate multiple AI agents on implementation, research, review, and test work. The dashboard is primarily for live triage: quickly seeing which agents are working, idle, blocked, errored, or done, then drilling into the right agent, task, or message without losing context.
Brand Personality
Focused, operational, and precise. The product should feel like a developer mission control surface: high-signal, technically credible, calm under pressure, and alive enough to make parallel work visible.
Aesthetic Direction
Use a mission-control visual language: dark, disciplined, status-rich, and spatially clear. Favor crisp hierarchy, meaningful status color, compact but readable density, and purposeful motion for live updates. Avoid generic AI dashboard tropes: decorative glow, arbitrary glassmorphism, identical metric cards, gradient-text hero treatments, and ornamental charts that do not support triage.
Design Principles
- Prioritize live triage over decoration: every region should answer who needs attention, what changed, and what the lead can inspect next.
- Preserve developer context: keep agents, tasks, activity, and timeline connected instead of scattering related signals across unrelated cards.
- Use status redundantly: pair color with text, shape, grouping, and accessible state labels so status is understandable without relying on color alone.
- Support both first glance and deep inspection: show a clear overview first, then reveal prompts, messages, dependencies, branches, and timing in focused detail views.
- Keep the interface fast and resilient: keyboard navigation, visible focus, responsive layout, reduced-motion support, and empty/error/loading states are baseline requirements.
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.
- today First seen · 483 lines · 4,577 tokens per session scan A a6db711ae58c
opencode-ensemble AGENTS.md is an instructions file published in the GitHub repository hueyexe/opencode-ensemble (212 stars, last pushed 7d ago), licensed MIT. It adds 4,577 tokens to every session, about $0.0229 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.
Other instructions, from other repositories
opencode.nvim AGENTS.md
Instructions for nickjvandyke/opencode.nvim, covering opencode.nvim — agent guide, what it is, entrypoints, config quirks and dependencies.
solo AGENTS.md
Instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
opencode-hive AGENTS.md
Instructions for rretsiem/opencode-hive, covering opencode hive, directory structure, ai setup instructions, step 1: discover available models and step 2: detect target project stack.
teamctl CLAUDE.md
Instructions for Alireza29675/teamctl, covering claude.md, what this repo is, stack and entry points, cross-cutting rules and how agents behave in this repo.
cool-workflow AGENTS.md
AGENTS.md instructions for coo1white/cool-workflow, covering cool workflow — autonomous development agent, quick index, role, hard rule — never push directly to main and iteration loop.
cc-skills CLAUDE.md
Instructions for rube-de/cc-skills, covering claude.md, plugins (claude code skills), navigation and claude code specifics.