agentleFS
Sign inStart free
ZaxbyHubZaxbyHub/opencode-swarm/.agents/skills/guardrail-patterns/SKILL.md

guardrail-patterns

Skill517 starsChanged 3 days agoMITView on GitHub

Codex 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.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use rg to locate the current guardrail section numbers before editing.

    line 19
  2. Very specific:

    Add or update adversarial tests for bypass surfaces, argument-order permutations, Windows shell forms, and .swarm path variants.

    line 21
  3. Distinctive:

    Run focused guardrail tests after the change and report exact commands.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Guardrail Patterns

Read, in order:

  1. AGENTS.md
  2. .agents/skills/engineering-conventions/SKILL.md
  3. .agents/skills/writing-tests/SKILL.md if tests are touched
  4. .opencode/skills/generated/guardrail-patterns/SKILL.md

Codex-specific execution notes:

  • Use rg to 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 .swarm path variants.
  • Run focused guardrail tests after the change and report exact commands.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free