Back to skills
SKILL.md
Agent Discipline
ASecuritytrigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code.
- 3 stars
- 0 votes
- 0 copies
- 0 views
- Added September 13, 2026
Works with
Security analysis
100/100npx -y skills add open-coder-ai/chock-catalog --skill agent-discipline --agent claude-codeAre you the author of Agent Discipline?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/open-coder-ai-agent-discipline)---
name: agent-discipline
description: "trigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code."
metadata:
chock.artifact: rule
chock.enforcement: advise
chock.coverage_without_chock: advisory
---
# Agent Discipline Rule
trigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code.
```
before(edit): read(file); before(done): verify(flow) + tests_pass + lint_clean; on_find(dead_code|unused): delete
never(fix_test_by): delete_assertion|weaken_check|skip; see(protect-test-integrity): deleted_test|assertion_loss|vacuous_assert; see(block-test-skips): added_skip|focus_marker(.only)
```
This skill is advisory: the client reading it has no mechanism to enforce it, and this policy stays advisory even when compiled by `chock` -- it ships rule text, not a blocking hook. See https://github.com/open-coder-ai/chock
Attribution
Comments
Loading comments…