Opencode Omo

Turn coding requests into completed work. Plan with Prometheus, execute with Atlas, and iterate with Sisyphus in OpenCode.

Security Scan

The skill is a workflow guide for OpenCode and largely matches its stated purpose, but its runtime instructions tell the agent to read a user config file and run local scripts (and to invoke the opencode agent) without safety checks — this could execute arbitrary code, so review before use.

Purpose & Capability

Name/description describe an OpenCode orchestration helper; the declared required binaries (opencode, git, clawhub) are coherent with that purpose. It is instruction-only (no code bundled), which matches a documentation/operational guide style.

Instruction Scope

The SKILL.md directs the agent/user to read ~/.config/opencode/opencode.json (a user config path not listed in required config paths) and to run local scripts (./scripts/check-omo.sh, ./scripts/run-ulw.sh) and commands that invoke opencode agents (e.g., opencode run --agent sisyphus...). Running those scripts or agent commands can execute arbitrary code in the current environment; the instructions do not include safety checks, explicit validation steps, or guidance to inspect script contents first. This is scope creep relative to a purely read-only helper and presents an execution risk.

Install Mechanism

No install spec is provided; the skill is instruction-only. This is the lowest-risk install mechanism because nothing from the skill is written to disk by default.

Credentials

The skill does not request environment variables, credentials, or declared config paths. The only requirements are binaries (opencode, git, clawhub), which are proportionate to the described functionality. However, the instructions still access a user config file (~/.config/opencode/opencode.json) even though it wasn't declared under required config paths.

Persistence & Privilege

always is false and the skill is user-invocable. It does not request persistent platform-level privileges or to modify other skills. (Note: autonomous invocation of skills is the platform default; that by itself is expected.)

What to consider before installing

This skill reads your OpenCode config and tells you to run local helper scripts and to invoke an OpenCode agent — those actions can execute arbitrary code in your environment. Before using it: 1) verify the opencode and clawhub binaries come from trusted sources and check their documentation; 2) inspect any ./scripts/*.sh helpers and ~/.config/opencode/opencode.json for unexpected behavior (network calls, credentials, destructive file ops); 3) run commands in an isolated environment (container or throwaway VM) first; 4) avoid running in sensitive repositories or on production systems until you're confident of the scripts' behavior. If the author can provide the helper scripts or more detail about what the opencode agent does and what the scripts perform, re-run this evaluation — that information would raise confidence and could change the verdict to benign.

OpenCode + Oh-My-OpenCode Operator

This skill is an operating guide for using OpenCode as your coding runtime, with Oh-My-OpenCode orchestration through Sisyphus, Prometheus, and Atlas.

What this skill gives you

• One-shot delivery with ulw for focused coding requests.
• Plan-to-execution workflow via @plan and /start-work.
• Repeatable defaults so code quality stays consistent across runs.

Core rules

• Do not edit code directly outside OpenCode unless explicitly asked.
• Prefer Sisyphus-first execution for coding tasks.
• For complex work: plan with Prometheus (@plan) then execute with Atlas (/start-work).

Quick start

Verify Oh-My-OpenCode plugin

cat ~/.config/opencode/opencode.json | grep "oh-my-opencode"

If the command returns output, the plugin is installed.

You can also run the bundled checker:

./scripts/check-omo.sh

Run one-shot coding (Sisyphus + ultrawork)

opencode run --agent sisyphus "ulw implement JWT auth in this service and add tests"

Or use the bundled helper:

./scripts/run-ulw.sh "implement JWT auth in this service and add tests"

Start interactive OpenCode (Sisyphus)

opencode --agent sisyphus

Inside OpenCode:

• Use @plan "..." to invoke Prometheus planning.
• Use /start-work to let Atlas execute the plan.

Failure handling

• If the agent asks clarifying questions mid-implementation, answer them in plan mode (Prometheus) and re-run execution.
• If you need more determinism, re-run with ulw and a smaller, explicit request.

Integration with other skills

• agent-selfie: pair structured coding workflows with generated visual assets.
• gemini-image-gen: use the same workflow discipline for image generation automations.
• agentgram: publish progress updates, findings, and demos produced from your workflow runs.

Changelog

• v0.3.0: Added bidirectional ecosystem links and bundled workflow helper scripts.
• v0.2.0: Reworked positioning, quick start, and metadata for clearer marketplace onboarding.
• v0.1.0: Initial release with Sisyphus/Prometheus/Atlas workflow guidance.