opencode-agent-creation-skill

opencode-agent-creation-skill is a skill for OpenCode from darellchua2/opencode-config-template. It costs 17 tokens per session (2,974 once invoked), scanned A, original, Apache-2.0.

A guide for creating OpenCode agents, which are configured assistants for specific coding tasks. It generates the required Markdown configuration and checks it against OpenCode's documentation.

In plain words
What is it for?
Use it to define an agent's purpose, mode, permissions, temperature, steps, and project-level or global location.
Why use it?
It removes repetitive configuration work and helps avoid invalid settings when creating primary or specialized helper agents.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions subagents; mentions OpenCode.

Good fit Use it to define an agent's purpose, mode, permissions, temperature, steps, and project-level or global location.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/darellchua2/opencode-config-template/opencode-agent-creation-skill
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.

Any agent
npx skills add darellchua2/opencode-config-template --skill opencode-agent-creation-skill
Clone the repo
git clone --depth 1 https://github.com/darellchua2/opencode-config-template

Made for: 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-agent-creation-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/opencode-agent-creation-skill.svg)](https://agentmods.dev/skills/darellchua2/opencode-config-template/opencode-agent-creation-skill)
Your own site
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/opencode-agent-creation-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/opencode-agent-creation-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,974 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 15
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 15
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Excessive Agency · line 173
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Rogue Agent · line 233
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Data Exfiltration · line 354
    Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.
    Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
How audits are shown
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 $0.00017 $0.02974
Opus 5 $0.00009 $0.01487
Sonnet 5 $0.00003 $0.00595
Haiku 4.5 $0.00002 $0.00297

Measured 4d ago against content hash 05af7e5dd018, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

opencode-agent-creation-skill 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 4d 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.

opencode_app/.opencode/skills/opencode-agent-creation-skill/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

  • Guide you through creating a new OpenCode agent by prompting for required configuration
  • Generate agent files in Markdown format with proper YAML frontmatter
  • Determine appropriate mode (primary or subagent) based on agent purpose
  • Configure permissions, temperature, steps, and other agent options
  • Create agent files in .opencode/agents/ (project) or ~/.config/opencode/agents/ (global)
  • Ensure description is provided and all required fields are set correctly
  • Validate frontmatter against current OpenCode documentation standards

When to use me

Use this when:

  • You want to create a new OpenCode agent without manually formatting configuration
  • You need to ensure your agent follows official documentation standards
  • You want to avoid repetitive setup when creating multiple agents
  • You're creating specialized subagents for specific tasks
  • You need to configure tool permissions and access levels

Ask clarifying questions about:

  • Agent's purpose and intended behavior
  • Mode: primary (main assistant) or subagent (specialized)
  • Required tool permissions
  • Whether it should be project-level or global

Prerequisites

  • Write access to .opencode/agents/ (project) or ~/.config/opencode/agents/ (global)
  • Understanding of OpenCode agent structure and frontmatter
  • Knowledge of the agent's purpose and required permissions

Steps

Step 1: Gather Agent Requirements

Prompt the user for the following information:

Required Fields:

  • Name: Agent identifier (lowercase, hyphens, e.g., code-reviewer)
  • Description: Brief description of what the agent does (REQUIRED)
  • Mode: primary or subagent

Configuration Options:

  • Model: Provider/model-id — primary agents use zai-coding-plan/glm-5.3 (1M context); subagents tier by purpose (see deploy/agent-tiers.json): glm-5.3 (reasoning/review/refactor), glm-5.3-flash (explore/low-impact and docs/lint), zai-coding-plan/glm-5.3-flash (vision — native multimodal, image/video/pdf input; image-analyzer-subagent/error-resolver-subagent run here and see images directly, no vision MCP server needed; zai-vision-analysis-skill calling glm-5v-turbo — a different model — is the direct-API fallback when native perception is unavailable). Never default a subagent to the primary tier.
  • Temperature: 0.0-1.0 (default: 0.7)
  • Steps: Max agentic iterations (default: 5)
  • Hidden: Hide from @ autocomplete (default: false, subagents only)
  • Color: UI color — hex or named value (e.g., primary, #FF5733)
  • Permissions: Tool access configuration

Read the full file on GitHub · 410 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. 4d ago First seen · 410 lines · 17 tokens per session scan A 05af7e5dd018

Subscribe to this mod's changes

opencode-agent-creation-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 2,974 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens