# Norms

> Track social norms, roles, obligations, permissions, sanctions, and place-specific expectations.

- **Type:** Skill
- **Install:** `agentstack add skill-alexanderj-carter-agentsociety2-agent-skills-norms`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [AlexanderJ-Carter](https://agentstack.voostack.com/s/alexanderj-carter)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [AlexanderJ-Carter](https://github.com/AlexanderJ-Carter)
- **Source:** https://github.com/AlexanderJ-Carter/AgentSociety2-Agent-Skills/tree/main/skills/norms
- **Website:** http://alexander.xin/AgentSociety2-Agent-Skills/

## Install

```sh
agentstack add skill-alexanderj-carter-agentsociety2-agent-skills-norms
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Norms

## Purpose

Model the agent as someone living under social rules. Norms shape what the agent feels expected, allowed, forbidden, admired, or punishable.

## Internal Logic (One Sentence)

Use place, role, audience, culture, relationship, routine, and observation context to estimate active norms, permissions, sanctions, visibility, and moral emotion risk in `state/norms.json`.

Research basis: `references/research_basis.md`.

## Use When

Use this skill in workplaces, schools, homes, public spaces, queues, restaurants, hospitals, religious places, legal settings, or any situation involving role expectations.

## Procedure

1. Read `state/observation.txt`, `state/observation_ctx.json`, `state/norms.json`, `state/culture.json`, `state/relationships.json`, `state/routine.json`, and profile context if present.
2. Identify active roles: worker, customer, parent, friend, stranger, patient, student, neighbor, host, guest.
3. Identify place-specific expectations and forbidden behaviors.
4. Estimate norm pressure, witness visibility, sanction risk, and moral emotion risk.
5. Write norm state for `cognition` and `plan`.

## Write

Write `state/norms.json`.

## Output Schema

```json
{
  "active_roles": ["customer", "stranger"],
  "active_norms": [
    {
      "norm": "wait in line",
      "pressure": 0.83,
      "violation_risk": 0.7,
      "likely_sanction": "disapproval"
    }
  ],
  "permissions": ["order food", "sit at available table"],
  "forbidden_or_costly": ["skip queue", "shout at staff"],
  "witness_visibility": 0.65,
  "moral_emotion_risk": {
    "shame": 0.35,
    "guilt": 0.2
  }
}
```

## Notes

Norms should influence `subjective_norm` in intention selection. A norm can be violated, but the violation should have social, emotional, or institutional consequences when visible or important.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [AlexanderJ-Carter](https://github.com/AlexanderJ-Carter)
- **Source:** [AlexanderJ-Carter/AgentSociety2-Agent-Skills](https://github.com/AlexanderJ-Carter/AgentSociety2-Agent-Skills)
- **License:** MIT
- **Homepage:** http://alexander.xin/AgentSociety2-Agent-Skills/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-alexanderj-carter-agentsociety2-agent-skills-norms
- Seller: https://agentstack.voostack.com/s/alexanderj-carter
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.