TheArchitectit/agent-guardrails-template
Skill OpenCode
Validates git commits follow COMMITWORKFLOW.md standards: AI attribution, single focus, no secrets.
not rated 1 today A SkillSpector: warn 23 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill OpenCode
Enforces TESTPRODUCTIONSEPARATION.md: production code first, separate instances, no data mixing.
not rated 1 today A SkillSpector: pass 24 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill OpenCode
Enforces the Four Laws of Agent Safety automatically on all operations. Halts on uncertainty.
not rated 1 today A SkillSpector: warn 23 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Insert honeypot tokens into sensitive files to detect if an agent leaks their contents in output.
not rated 1 today A SkillSpector: warn 22 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Topic-based content filtering to block harmful or unauthorized content in agent output.
not rated 1 today A SkillSpector: pass 18 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.
not rated 1 today A SkillSpector: pass 23 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Available guardrail tools and automatic enforcement behavior for pi agents.
not rated 1 today C 16 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
How to use and interpret the guardrails panel and status bar in the pi TUI.
not rated 1 today A SkillSpector: pass 22 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Detect and block prompt injection attacks in tool input (bash commands, write/edit content) before execution.
not rated 1 today B SkillSpector: warn 23 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Prevent sensitive data (secrets, credentials, PII) from leaking in agent output.
not rated 1 today A SkillSpector: pass 24 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
How guardrail policies cascade from organization through team to project level.
not rated 1 today A SkillSpector: pass 17 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.
not rated 1 today A SkillSpector: warn 19 tokens
original BSD-3-Clause
TheArchitectit/agent-guardrails-template
Skill Claude CodeCodex
Per-tool permission levels (auto/ask/blocked) that gate which tools the agent can use.
not rated 1 today A SkillSpector: warn 23 tokens
original BSD-3-Clause
guardrails
14TheArchitectit/agent-guardrails-template
MCP server Claude CodeCodexCursor +2
MCP server "guardrails", hosted remotely at localhost, as configured in TheArchitectit/agent-guardrails-template.
not rated 1 today A
tokens not measured
original BSD-3-Clause
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: