Guardrail Patterns
SkillDev toolsCodex adapter for opencode-swarm destructive-command guardrail changes. Use before modifying src/hooks/guardrails.ts, checkDestructiveCommand, dcNormalizeCommand, shell-wrapper parsing, .swarm destructive-command blocking, or guardrails unit/adversarial tests.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Guardrail Patterns skill
What this skill tells your AI
The instructions your AI receives, as published by zaxbyhub/opencode-swarm in .agents/skills/guardrail-patterns/SKILL.md and read by ahel’s review.
Read, in order:
AGENTS.md.agents/skills/engineering-conventions/SKILL.md.agents/skills/writing-tests/SKILL.mdif tests are touched.opencode/skills/generated/guardrail-patterns/SKILL.md
Codex-specific execution notes:
- Use
rgto locate the current guardrail section numbers before editing; line numbers in generated skills can drift. - Preserve wrapper-unwrapping, normalization, and per-segment evaluation order unless the task is specifically to change it.
- Add or update adversarial tests for bypass surfaces, argument-order permutations, Windows shell forms, and
.swarmpath variants. - Run focused guardrail tests after the change and report exact commands.
Signals
- GitHub stars
- 467
- Forks
- 51
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
guardrail-patterns- Source
- github.com/zaxbyhub/opencode-swarm