---
id: agent-discipline
track: coding
version: 0.0.4
label: advisory
keyword: advise
where: text
sha256: c7df9d364b5e6dbd1d8ffd7c7bdeb72d50c6cf2de52728910f6a69e495e2b164
source: https://github.com/open-coder-ai/chock-catalog/tree/1e60d211c1bb767152c6ab0167932da06ab3a10f/base/agent-discipline
catalog_ref: 1e60d211c1bb767152c6ab0167932da06ab3a10f
---

# Agent Discipline

agent-discipline · version 0.0.4

Advisory — Advisory only. It is skill text, and nothing stops a violation. Chock adds friction. It is not a security boundary. 

In a git repo: advisory (The agent reads the text, and nothing stops a violation.)



## What it does

Trigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code.

## Its label on each agent

- Claude Code (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=claude-code&p=agent-discipline
- Cursor (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=cursor&p=agent-discipline
- Codex (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=codex&p=agent-discipline
- GitHub Copilot (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=copilot&p=agent-discipline
- Devin (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=devin&p=agent-discipline
- Grok (tested): Not graded yet for Grok. Builder: /coding/builder/#client=grok&p=agent-discipline
- goose (tested): Not graded yet for goose. Builder: /coding/builder/#client=goose&p=agent-discipline
- Antigravity (tested): Not graded yet for Antigravity. Builder: /coding/builder/#client=antigravity&p=agent-discipline
- OpenHands (untested): Not graded yet for OpenHands. Builder: /coding/builder/#client=openhands&p=agent-discipline
- Kimi Code (untested): Not graded yet for Kimi Code. Builder: /coding/builder/#client=kimi-code&p=agent-discipline
- Factory Droid (untested): Not graded yet for Factory Droid. Builder: /coding/builder/#client=factory-droid&p=agent-discipline

## What it misses

This policy does not state what it misses.

## Latest change

0.0.4 · 2026-10-27 — Title wording only (IR-F40): "Agent Discipline Rule" is now "Agent Discipline". The id, guard and tests are unchanged.

## Provenance

- Tested by 0 of 3 cases run automatically
- SHA-256: `c7df9d364b5e6dbd1d8ffd7c7bdeb72d50c6cf2de52728910f6a69e495e2b164`
- Catalog commit: https://github.com/open-coder-ai/chock-catalog/commit/1e60d211c1bb767152c6ab0167932da06ab3a10f
- Source: https://github.com/open-coder-ai/chock-catalog/tree/1e60d211c1bb767152c6ab0167932da06ab3a10f/base/agent-discipline (catalog path `base/agent-discipline`)
- Presets: Agent craft
- JSON: `/api/coding/policies/agent-discipline.json`
- Report a problem: https://chock.sh/report/?policy=agent-discipline&version=0.0.4&page=%2Fcoding%2Fpolicies%2Fagent-discipline%2F