원클릭으로
sg
Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | sg |
| description | Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions. |
Superego provides metacognitive review for AI sessions, catching premature commitment, scope creep, and misalignment.
All commands invoke the sg CLI. If sg is not installed, show:
sg not installed. Install with:
brew tap open-horizon-labs/homebrew-tap && brew install superego
# or: cargo install superego
Review staged changes or current work. On-demand metacognitive evaluation.
sg review
Initialize superego for this project.
sg init
Review decision history with LLM analysis.
sg audit
Query decision history.
sg history
List available superego prompts.
sg prompt list
Switch to a different superego prompt.
sg prompt switch <name>
Show current prompt content.
sg prompt show
Show current evaluation mode (always or pull).
sg mode
Reset superego state (recovery from corruption).
sg reset
Check hooks and auto-update if outdated.
sg check
Mode: Pull mode - evaluates only when explicitly requested.
When to use $sg review:
Results:
has_concerns: true = STOP and show feedback to userhas_concerns: false = continue with confidenceskipped: true = proceed normally (this is fine)Superego is opt-in. Use it for high-stakes decisions, architectural choices, or when you want a second opinion.
Address PR comments for GitHub issue PRs, resolve feedback, push fixes
Open Horizon Labs meta-tool. One entry point for ba, wm, and superego. Use "bottle-init" to set up all tools, "bottle-status" to check state.
Task tracking. "$ba status" for current tasks, "$ba claim <id>" to start work, "$ba finish <id>" when done.
Open Horizon Labs orchestration. "$bottle init" for setup, "$bottle dive" to start sessions, "$bottle web-context" for fresh docs.
Working memory. "$wm dive" to prep sessions, "$wm compile" for context, "$wm distill" to extract learnings.