opencode-hive AGENTS.md

Project instructions for OpenCode Hive, a template that installs a multi-agent setup into other coding projects.

In plain words
What is it for?
Use them when installing or configuring OpenCode Hive, selecting models for different jobs, or adapting its agents and rules to a project.
Why use it?
They define how to choose available models and identify the target project's technology before configuring the setup.

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/rretsiem/opencode-hive/agents-md
Clone the repo
git clone --depth 1 https://github.com/rretsiem/opencode-hive

Made for: Codex, OpenCode.

Per session 1,233 This file is loaded in full into every session.
When invoked 1,233 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 $0.01233 $0.01233
Opus 5 $0.00616 $0.00616
Sonnet 5 $0.00247 $0.00247
Haiku 4.5 $0.00123 $0.00123

Measured 2d ago against content hash 0e999b220cde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-hive 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCode Hive

A multi-agent architecture for OpenCode. This is a template -- not a project to develop, but a system to install into other projects.

Directory Structure

  • global/ -- Files to install at ~/.config/opencode/ (agents, tools, scripts, rules, skills)
  • project/ -- Files to install at .opencode/ in the target project
  • examples/ -- Optional specialist agents to pick based on project stack
  • docs/ -- Guides for model selection, adding specialists, architecture

AI Setup Instructions

When a user asks you to "set this up", "install this", or "configure my project":

Step 1: Discover Available Models

Run opencode models and present the output. Ask the user:

  • "Which of these providers are subscription/free (no per-token cost)?"
  • "Which provider/model do you want for code generation?"

Categorize into three tiers:

  • SUB: Subscription models -- for routing, planning, review, wiki
  • MID: Pay-per-token coding models -- for implementation specialists
  • PREMIUM: Frontier models -- never assign as default, manual override only

Step 2: Detect Target Project Stack

Ask the user for the target project path, then scan it:

ls <target>/*.py <target>/*.ts <target>/*.go <target>/*.rs 2>/dev/null | head -20
ls <target>/package.json <target>/pyproject.toml <target>/go.mod <target>/Cargo.toml 2>/dev/null
ls <target>/Dockerfile <target>/docker-compose* 2>/dev/null

Step 3: Install Global Files

Copy each global/ folder to ~/.config/opencode/:

  • agents/*.md, tools/*.ts, scripts/*, skills/*/, rules/*.md
  • Merge opencode.json — don't overwrite existing MCP, LSP, or plugin config

Ask before overwriting any existing files.

Step 4: Replace Model Placeholders

In all copied files, replace these four placeholders with real model IDs:

  • YOUR_ROUTING_MODEL -> fast, reliable model for routing
  • YOUR_ANALYSIS_MODEL -> strong model for planning and review
  • YOUR_FAST_MODEL -> inexpensive model for titles and summaries
  • YOUR_CODE_MODEL -> strongest available code-generation model

Read the full file on GitHub · 108 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 · 108 lines · 1,233 tokens per session scan A 0e999b220cde

Subscribe to this mod's changes

opencode-hive AGENTS.md is an instructions file published in the GitHub repository rretsiem/opencode-hive (39 stars, last pushed 1mo ago), licensed MIT. It adds 1,233 tokens to every session, about $0.0062 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.