opencode-config-template: Instructions file for Codex

AGENTS.md

opencode-config-template AGENTS.md is an instructions file for Codex, OpenCode from darellchua2/opencode-config-template. It costs 3,521 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for a configurable OpenCode setup, including where its source files live and how installations are deployed.

In plain words
What is it for?
Use them when changing the repository's agents, skills, deployment scripts, Docker setup, or installation commands. They direct edits to the source configuration before redeployment.
Why use it?
They prevent edits in generated copies and clarify how to manage secrets, dependencies, and installation targets.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is darellchua2/opencode-config-template's own configuration. It tells Codex and OpenCode how to work on opencode-config-template 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-config-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to darellchua2/opencode-config-template. 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/darellchua2/opencode-config-template/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

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-config-template AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/darellchua2/opencode-config-template/agents-md/github.svg)](https://agentmods.dev/instructions/darellchua2/opencode-config-template/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/darellchua2/opencode-config-template/agents-md"><img src="https://agentmods.dev/badge/instructions/darellchua2/opencode-config-template/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-config-template AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/darellchua2/opencode-config-template/agents-md"><img src="https://agentmods.dev/badge/instructions/darellchua2/opencode-config-template/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,521 This file is loaded in full into every session.
When invoked 3,521 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 $0.03521 $0.03521
Opus 5.5 $0.01408 $0.01408
Sonnet 5.5 $0.00704 $0.00704
Haiku 4.5 $0.00352 $0.00352

Measured 1mo ago against content hash 346473e6e704, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opencode-config-template 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 1mo 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository-Specific Agent Instructions

Repo conventions only. Usage docs (install, deploy commands, file tree, chaining syntax) live in README.md and user-level deploy/.AGENTS.md (deploys to ~/.config/opencode/AGENTS.md). Do not duplicate here.

Repository Purpose

Multi-mode OpenCode configurator:

  1. User-space deploy — ./deploy/setup.sh copies config, agents, skills to ~/.config/opencode/.
  2. Docker standalone — docker compose up -d launches a web endpoint via opencode_app/.
  3. Individual install — npx github:darellchua2/opencode-config-template add <name> pulls the named skill/agent plus its declared prerequisites (dependency-map.json requiresSkills auto-installs them with a notice; --no-deps opts out) (shadcn-style copy model). Default target ~/.config/opencode/ (auto-discovered, no config touch); --project opts into ./.opencode/; --target claude|both writes ~/.claude/skills/ (Agent Skills open standard; --format is a deprecated alias) and — since #457 — agents to ~/.claude/agents/ with additive permissions→tools/disallowedTools translation + synthesized name: (lossy, warned); --target agents writes the cross-tool shared ~/.agents/{agents,skills}/ (read by Kimi Code and pi; verbatim copies, agents model-unpinned); agents/claude targets have no project destination — --project with them notes and uses the opencode project target (test-pinned behavior, #454/#455); --target kimi writes Kimi Code native dirs (~/.kimi-code/{agents,skills}/ user, .kimi-code/{agents,skills}/ project) with additive permissions→tools/disallowedTools translation (lossy, warned); --target kilo writes Kilo Code native dirs (~/.config/kilo/agent/ + ~/.kilo/skills/ user, .kilo/{agents,skills}/ project) with additive permissions→permission-map translation (lossy, warned). See issue #304.

Source of Truth

The root skills/ and agents/ dirs are the single source for skills and agents. Never edit deployed ~/.config/opencode/ copies — edit source, then redeploy.

Read the full file on GitHub · 140 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. 1mo ago Changed · +18 lines · +384 tokens per session 346473e6e704
  2. 1mo ago Changed · +265 tokens per session 2c9a6d113880
  3. 1mo ago Changed · +9 lines · +469 tokens per session 195f5222380c
  4. 1mo ago Changed · +1 lines · +63 tokens per session b276cc4f0b08
  5. 1mo ago Changed · +19 tokens per session 65eafafdb6d2
  6. 1mo ago Changed · +94 tokens per session 6131c0b2d641
  7. 1mo ago Changed · +85 tokens per session ed4ba6195d53
  8. 2mo ago Changed · -16 tokens per session 4f84274f58fa
  9. 2mo ago First seen · 112 lines · 2,158 tokens per session scan A cc28ef7b2350

Subscribe to this mod's changes

opencode-config-template AGENTS.md is an instructions file published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,521 tokens to every session, about $0.0141 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 2026-08-31.

Related

opencode-config-template AGENTS.md compared with instructions from other repositories

opencode-config-template AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opencode-config-template AGENTS.mddarellchua2/opencode-config-templateInstructions file61mo agoApache-2.0A3,521Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub 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