opencode-swarm AGENTS.md

opencode-swarm AGENTS.md is an instructions file for Codex, OpenCode from ZaxbyHub/opencode-swarm. It costs 6,774 tokens per session, scanned A, original, MIT.

A repository instruction file that defines the rules automated coding tools and contributors must follow before changing code.

In plain words
What is it for?
Guiding code changes, test edits, issue investigation, commits, pull requests, and swarm-based development work.
Why use it?
It reduces inconsistent changes by making required reading, working locations, and engineering constraints explicit.

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/zaxbyhub/opencode-swarm/agents-md
Clone the repo
git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for opencode-swarm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zaxbyhub/opencode-swarm/agents-md.svg)](https://agentmods.dev/instructions/zaxbyhub/opencode-swarm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zaxbyhub/opencode-swarm/agents-md"><img src="https://agentmods.dev/badge/instructions/zaxbyhub/opencode-swarm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,774 This file is loaded in full into every session.
When invoked 6,774 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.06774 $0.06774
Opus 5 $0.03387 $0.03387
Sonnet 5 $0.01355 $0.01355
Haiku 4.5 $0.00677 $0.00677

Measured yesterday against content hash eb8a66b3a845, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-swarm 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 yesterday.

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.

- Windows is first-class. Handle `.cmd` extensions for npm/bun binaries, PATH differences, and the fact that `child_process.spawn('bin', ...)` does not behave identically to `cmd.exe`.
AGENTS.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Engineering contract for opencode-swarm

This file is the root engineering contract for opencode-swarm. It applies to every contributor — human, Claude Code, OpenCode agent, or other automated tool. Read it fully before making any code change. It is intentionally short and operational; the long-form rationale and historical failure map live in docs/engineering-invariants.md.

Required reading order

When you are about to do… Read these (in order)
Any code change AGENTS.md (this file) → docs/engineering-invariants.md (skim, deep-dive on touched invariants)
Write or modify any test file this file → .opencode/skills/writing-tests/SKILL.md (or .claude/skills/writing-tests/SKILL.md for Claude)
Commit / push / open a PR this file → .claude/skills/commit-pr/SKILL.md
Trace, investigate, root-cause, fix, or resolve an issue or bug this file → .opencode/skills/issue-tracer/SKILL.md (or .claude/skills/issue-tracer/SKILL.md for Claude)
Swarm-mode Claude work this file → CLAUDE.md.claude/session/swarm-mode.md (when present)
Architecture / plugin init / subprocess / tool-registration / plan-durability / .swarm storage / runtime-portability change this file → docs/engineering-invariants.md.opencode/skills/engineering-conventions/SKILL.md (or .claude/skills/engineering-conventions/SKILL.md)

AGENTS.md and docs/engineering-invariants.md together are the single source of truth for repository invariants. When CLAUDE.md, contributing.md, TESTING.md, or any skill conflicts with this file, this file wins; that skill or doc is out of date and must be reconciled.

Prime directive

Preserve the runtime contracts that keep the plugin loadable, portable, bounded, recoverable, and safe across Windows, macOS, Linux, GUI, TUI, Bun, and Node-hosted plugin contexts.

A plugin that loads on macOS but hangs Desktop Windows is a regression. A change that passes locally on one platform but corrupts state on another is a regression. Default to "what could go wrong on the host I am not testing on?"

Read the full file on GitHub · 172 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. yesterday First seen · 172 lines · 6,774 tokens per session scan A eb8a66b3a845

Subscribe to this mod's changes

opencode-swarm AGENTS.md is an instructions file published in the GitHub repository ZaxbyHub/opencode-swarm (462 stars, last pushed today), licensed MIT. It adds 6,774 tokens to every session, about $0.0339 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 2026-09-03.

Related

Other instructions, from other repositories

dev-3.0 CLAUDE.md

Claude Code instructions for h0x91b/dev-3.0, a project described as: Mission control for the One Person Studio — run a fleet of AI coding agents in parallel without losing your mind. Kanban + git worktrees + tmux for Claude Code, Codex, Gemini CLI, OpenCode and any shell agent. Not an IDE.

h0x91b/dev-3.0 · 3 tokens

dev-3.0 AGENTS.md

AGENTS.md instructions for h0x91b/dev-3.0, covering agents.md, response style, what is this, ui/ux work — which skill, and when and where dev3 overrides the better-family skills.

h0x91b/dev-3.0 · 12,073 tokens

coco-workflow CLAUDE.md

Instructions for skullninja/coco-workflow, covering claude.md -- coco, project overview, architecture, key files and tracker (lib/tracker.sh).

skullninja/coco-workflow · 7,598 tokens

Maestro CLAUDE.md

Instructions for aaryansinha16/Maestro, covering maestro — claude.md, project identity, core operating principles, how it works and the conductor (brain).

aaryansinha16/Maestro · 3,702 tokens

product-mode CLAUDE.md

Instructions for sohaibt/product-mode, covering claude.md product-led collaboration guidelines, pre-flight checklist, the seven principles, 1. frame the problem before the solution and 2. make assumptions & unknowns visible.

sohaibt/product-mode · 1,792 tokens

builders-stack AGENTS.md

Instructions for lonormaly/builders-stack, covering agents.md — the primer for coding agents, rule zero — worktrees are temporary and share dependencies, 1. the mental model — the buckets, 2. the map — all 17 packages and 3. the laws — do not break these.

lonormaly/builders-stack · 5,977 tokens