Agent skill

Create Opencode Agents

by sandgardenhq in sandgardenhq/sgai

Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes.

Custom licenceAuto-check passed

Install Create Opencode Agents

skills CLI
$ npx skills add sandgardenhq/sgai --skill create-opencode-agents -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sandgardenhq/sgai create-opencode-agents --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sandgardenhq/sgai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cmd/sgai/skel/.sgai/skills/meta/create-opencode-agents .claude/skills/create-opencode-agents && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
create-opencode-agents
GitHub stars
137
Token cost
~1.8k tokens
SKILL.md length
781 words
Files
1
Skills in repo
53
Repo updated
First seen
Licence
Custom licence

At a glance

Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes.

  • Works in 5 steps: Define Agent Purpose → Research Configuration Options → Configure for Task → …
  • Updating agents for coordination
  • SKILL.md covers Overview, When to Use, Core Pattern and Implementation, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Create Opencode Agents is an agent skill from sandgardenhq/sgai. Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes. Use when creating or updating agents for coordination, implementation, review, deployment, verification, documentation, or specialized workflows.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Sandgarden AI Software Factory.

When your agent uses it

  • Updating agents for coordination
  • Specialized workflows

Example prompts

  • “/create-opencode-agents”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Define Agent Purpose
  2. Research Configuration Options
  3. Configure for Task
  4. Create Configuration File
  5. Test Configuration

What it can do on your machine

Read from SKILL.md and the folder at commit 9efbb7b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Create Opencode Agents loads about 1.8k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 781 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 781 words (~1,791 tokens).

“OpenCode agents are specialized AI assistants configured for specific tasks with custom prompts, models, tools, permissions, and message contracts. Creating effective SGAI agents requires bounded context packets, explicit work splitting, and strict return envelopes.”

— opening of SKILL.md by sandgardenhq, Custom licence
name
create-opencode-agents

Read the full SKILL.md on GitHub

Files

Just SKILL.md in cmd/sgai/skel/.sgai/skills/meta/create-opencode-agents of sandgardenhq/sgai.

Open the folder on GitHubat commit 9efbb7b

Compare with similar skills

Create Opencode Agents next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Create Opencode Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Opencode Agents this skillsandgardenhq/sgai137—~1.8kAutomated safety check: PassCustom licence
Permission Managersickn33/agentic-awesome-skills47k1 repos~595Automated safety check: PassMIT
Cognee Permissionstopoteretes/cognee32k—~3.6kAutomated safety check: PassApache-2.0
Fewer Permission Promptsasgeirtj/system_prompts_leaks69k—~1.9kAutomated safety check: PassCC0-1.0
Permissions Policythedaviddias/Front-End-Checklist74k—~565Automated safety check: PassMIT
Auditing GCP Iam Permissionsmukul975/Anthropic-Cybersecurity-Skills34k—~3.2kAutomated safety check: PassApache-2.0

Similar skills

  • Permission Manager

    sickn33/agentic-awesome-skills

    Manage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patterns

    47k GitHub starsUsed in 1 repo~595 tokens
    DevelopmentAuto-check passed
  • Cognee Permissions

    topoteretes/cognee

    A skill your agent uses when working with cognee's users, permissions, and multi-tenancy — creating users, tenants and roles, sharing datasets (read/write/delete/share grants), acting as a specific…

    32k GitHub stars~3.6k tokensUpdated today
    Backend & APIsAuto-check passed
  • Fewer Permission Prompts

    asgeirtj/system_prompts_leaks

    Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.

    69k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Permissions Policy

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing HTTP response headers for defense-in-depth security hardening on any web application.

    74k GitHub stars~565 tokensUpdated 2 days ago
    SecurityAuto-check passed
  • Auditing GCP Iam Permissions

    mukul975/Anthropic-Cybersecurity-Skills

    Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI…

    34k GitHub stars~3.2k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Add Permission

    fullstackhero/dotnet-starter-kit

    Add a new permission end-to-end — server constant + endpoint gate, and (admin app) mirror it into the permissions catalog + route guard.

    6.8k GitHub stars~849 tokensUpdated 8 days ago
    Backend & APIsAuto-check passed

More from sandgardenhq/sgai

All 53 skills in this repo
  • Root Cause Tracing

    sandgardenhq/sgai

    A skill your agent uses when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation…

    137 GitHub starsUsed in 4 repos~1.4k tokens
    Auto-check passed
  • Condition Based Waiting

    sandgardenhq/sgai

    A skill your agent uses when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state…

    137 GitHub starsUsed in 3 repos~933 tokens
    Auto-check passed
  • Defense In Depth

    sandgardenhq/sgai

    A skill your agent uses when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally…

    137 GitHub starsUsed in 3 repos~970 tokens
    Auto-check passed
  • Agent Native Architecture

    sandgardenhq/sgai

    Build AI agents using prompt-native architecture where features are defined in prompts, not code.

    137 GitHub stars~2k tokensUpdated 17 days ago
    Auto-check passed
  • Adhoc

    sandgardenhq/sgai

    Run and manage ad-hoc AI prompts in sgai workspaces without starting a full agentic session.

    137 GitHub stars~1.2k tokensUpdated 17 days ago
    Auto-check passed
  • You must use this skill when debugging web UI bugs or testing interactive components that require multi-step browser interactions.

    137 GitHub stars~3.7k tokensUpdated 17 days ago
    Auto-check passed

Questions about Create Opencode Agents

What does Create Opencode Agents do?

Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes. Create Opencode Agents is an agent skill from sandgardenhq/sgai. Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes.

When should I use Create Opencode Agents?

Create Opencode Agents fits situations like: updating agents for coordination; specialized workflows.

How do I install Create Opencode Agents in Claude Code?

Run `npx skills add sandgardenhq/sgai --skill create-opencode-agents -a claude-code`. Or copy the skill folder (cmd/sgai/skel/.sgai/skills/meta/create-opencode-agents in sandgardenhq/sgai) into .claude/skills/create-opencode-agents in your project. Claude Code loads it when a task matches its description.

How do I install Create Opencode Agents in Codex?

Run `npx skills add sandgardenhq/sgai --skill create-opencode-agents -a codex`. Or copy the skill folder (cmd/sgai/skel/.sgai/skills/meta/create-opencode-agents in sandgardenhq/sgai) into .agents/skills/create-opencode-agents in your project. Codex loads it when a task matches its description.

Can I use Create Opencode Agents in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sandgardenhq/sgai --skill create-opencode-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-opencode-agents, .gemini/skills/create-opencode-agents, .github/skills/create-opencode-agents and .opencode/skills/create-opencode-agents in your project.

What does Create Opencode Agents need to run?

SKILL.md names no scripts, command-line tools or credentials: Create Opencode Agents is instructions for the agent only.

Does Create Opencode Agents access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Create Opencode Agents safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Create Opencode Agents use?

Create Opencode Agents has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Create Opencode Agents use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Create Opencode Agents?

Skills that share tags, products or a category with Create Opencode Agents: Permission Manager (sickn33/agentic-awesome-skills, 47k stars), Cognee Permissions (topoteretes/cognee, 32k stars), Fewer Permission Prompts (asgeirtj/system_prompts_leaks, 69k stars) and Permissions Policy (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Opencode Agents?

sandgardenhq (a GitHub organization) maintains it in sandgardenhq/sgai, which has 137 GitHub stars. The repository holds 53 skills in this directory. The repository was last updated on September 21, 2026.

Source: sandgardenhq/sgai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.