Soma Governance — AI skill for Claude Code
Soma makes AI agents trustworthy by providing observably traceable governance, evidence-based rule selection W/ JIT, AST analysis tools, TTC Verifiers, and adaptive rule lifecycle management.
How to install Soma Governance
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open nseney1/Soma-Governance and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Soma Governance does
Soma makes AI agents trustworthy by providing observably traceable governance, evidence-based rule selection W/ JIT, AST analysis tools, TTC Verifiers, and adaptive rule lifecycle management.
Alternatives in AI
- Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
- Model Selection — Model Selection & Task Tool 1.1k ★
- Claudekit — by Carl Rannaberg - Impressive CLI toolkit providing auto-save checkpointing, code quality hooks, specificatio 633 ★
README
Soma
[](LICENSE) [](#-core-rules) [](#-agent-skills) [](#%EF%B8%8F-automation-scripts) [](docs/project/CHANGELOG.md) [](#) [](https://dev.to/nseney1/your-ai-agents-rules-file-is-a-gentlemans-agreement-heres-what-happens-when-you-build-2dml) [](https://m8ven.ai/mcp/nseney1/soma-governance?s=readme)
**Governance framework that makes AI coding agents trustworthy.**
Soma makes AI agents trustworthy by providing observably traceable governance — evidence-based rule selection, AST analysis tools, and adaptive rule lifecycle management. Rules that stop proving themselves expire. Rules that keep proving themselves get promoted. Claims that don't match evidence are caught.
**The Problem**: Ungoverned AI coding agents waste significant portions of tokens in circular rework loops, hallucinated API calls, and broken assumptions. Static rule files (`.cursorrules`, `CLAUDE.md`) help but never adapt, and the agent can simply ignore them.
**The Solution**: Soma provides JIT context injection, adaptive rule lifecycle, and pre-commit enforcement hooks to reduce waste. Rules are scored by Wilson-bounded fitness intervals and pruned when they stop proving value.
**Internal naming convention**: Soma uses a biological metaphor internally (genome, enzymes, organs, cells) to mo
Related Skills
Dsh Tech Selection
Stop letting your AI guess — a research protocol for tech decisions that any AI agent (DSH/Claude/Cursor/Codex
Caio
Chief AI Officer review — AI/ML governance, model lifecycle, responsible AI, LLM integration patterns
Clawdcontext4vscode
Enhance VS Code with ClawdContext, providing Markdown-based context management for efficient AI coding agent w
AI Prompts
A comprehensive collection of AI prompts designed for complete software development lifecycle management withi
Cc Skill Product Lifecycle Orchestrator
AI-collaborative product lifecycle management skill for Claude Code. Script-enforced phase gates from PRD to d
Agent Session.Nvim
A Neovim plugin for managing multiple AI agent sessions (Claude Code, terminal agents, LLM CLI sessions) with
Related Agents
Multi Agent Systems Architect Agent
Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — cover
Engineering Multi Agent Systems Architect
Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — cover
Tier2 Auditor
Tier 2, read-only auditor. Call it by name when you want a rule-by-rule check against fixed rules, a checklist