opencode: Instructions file for Codex

AGENTS.md

opencode AGENTS.md is an instructions file for Codex, OpenCode from Awish021/opencode. It costs 603 tokens per session, scanned A, original, MIT.

Project instructions for OpenCode, covering how an AI coding assistant should collaborate, plan work, research choices, test changes, and keep the codebase tidy.

In plain words
What is it for?
Starting tasks, reviewing changes, choosing technical approaches, testing code, and keeping work focused in the OpenCode project.
Why use it?
They provide consistent rules for making careful changes and avoiding rushed fixes, unnecessary dependencies, and leftover code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents.

This is Awish021/opencode's own configuration. It tells Codex and OpenCode how to work on opencode itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything opencode configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Awish021/opencode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Awish021/opencode/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Awish021/opencode

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/awish021/opencode/agents-md/github.svg)](https://agentmods.dev/instructions/awish021/opencode/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/awish021/opencode/agents-md"><img src="https://agentmods.dev/badge/instructions/awish021/opencode/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for opencode AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/awish021/opencode/agents-md"><img src="https://agentmods.dev/badge/instructions/awish021/opencode/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 603 This file is loaded in full into every session.
When invoked 603 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00603 $0.00603
Opus 5.5 $0.00241 $0.00241
Sonnet 5.5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 2mo ago against content hash 79e1c020c4e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opencode 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 2mo 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working Together

These guidelines define how we collaborate. They are required baseline behavior.

Quick Obligations

Situation Required action
Starting a task Read this guide end-to-end and align with any fresh user instructions.
Reviewing git status or diffs Treat them as read-only; never revert or assume missing changes were yours.
Adding a dependency Research well-maintained options and confirm fit with the user before adding.

Mindset & Process

  • Think before implementing. Rushing causes shallow fixes that break later.
  • Do not leave breadcrumbs when moving or deleting code. Remove obsolete comments such as "// moved to X" or "relocated".
  • Stay focused on the core problem and avoid tangents.
  • Fix root causes, not symptoms.

When taking on new work, follow this sequence:

  1. Think about the architecture.
  2. Research official docs, blogs, or papers on the best architecture.
  3. Review the existing codebase.
  4. Compare the research with the codebase to choose the best fit.
  5. Implement the fix or ask about the tradeoffs the user is willing to make.
  • Write code that is clear and straightforward.
  • Leave the codebase better than you found it. Fix confusing names, dead code, and messy patterns when you see them.
  • Delete unused parameters, dead helpers, and obsolete code, then update callers.
  • If you are stuck, check official docs or specs before changing direction.
  • Use subagents for parallel or independent work whenever possible.
  • If there is even a 1% chance a skill applies, you must invoke it.

When code is confusing:

  1. Simplify it if you can.
  2. Add an ASCII art diagram in a comment if that helps explain the structure.

Testing Philosophy

Test everything. Be thorough so regressions are caught early.

Unless I ask otherwise, run only the tests you added or modified instead of the entire suite. Don't waste time on what hasn't changed.

Never ask me to run the tests to confirm, run them yourself to confirm.

Read the full file on GitHub · 62 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. 2mo ago First seen · 62 lines · 603 tokens per session scan A 79e1c020c4e3

Subscribe to this mod's changes

opencode AGENTS.md is an instructions file published in the GitHub repository Awish021/opencode (11 stars, last pushed 4mo ago), licensed MIT. It adds 603 tokens to every session, about $0.0024 per session on Opus 5.5. 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.

Related

opencode AGENTS.md compared with instructions from other repositories

opencode AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opencode AGENTS.mdAwish021/opencodeInstructions file114mo agoMITA603Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot