thearchitectit/agent-guardrails-template/docs-access

Claude Code and agent skill by thearchitectit/agent-guardrails-template

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.

Install

npx vskill@latest install thearchitectit/agent-guardrails-template/docs-access

SKILL.md

Guardrails Docs Access

Provides runtime access to guardrails skill documentation and configuration guides.

Skill Documentation Index

SkillDescriptionConfig Reference
guardrails-coreCore guardrails lifecycle, tools, and coverage map.guardrails/config.json
injection-defensePrompt injection detection and blockinginjection.patterns[], injection.confidenceThreshold
output-securityOutput validation for secrets, PII, and code patternsoutputValidation.rules[]
content-safetyTopic-based content filtering (deny/allow lists)outputValidation.contentFilter.deniedTopics
tool-permissionsPer-tool allow/block/ask permission policiestoolPermissions.tools{}
policy-configDynamic policy management with rollbackpolicy.name, policy.version
sandbox-isolationContainer sandbox configuration and enforcementsandbox.enabled, sandbox.type
canary-tokensCanary token generation, embedding, and detectioncanary.prefix, canary.tokenLength
guardrails-dashboardDashboard UI for violation monitoring and controlsN/A

Usage

List All Skills
typescript
const skills = guardrail_list_skills(); // Returns array of skill metadata
Read a Specific Skill
typescript
const content = guardrail_read_skill({ skill: "injection-defense" }); // Returns SKILL.md content
Read Language Rule Files
typescript
const rules = guardrail_read_language_rules({ language: "python" }); // Returns rules JSON
Get Available Languages
typescript
const langs = guardrail_list_languages(); // Returns ["python", "typescript", "go", "rust"]

Configuration Templates

Minimal Config
json
{
"enabled": true,
"enabledRules": ["four-laws", "scope-validator", "halt-when-uncertain"]
}
With Output Validation
json
{
"enabled": true,
"enabledRules": ["four-laws", "scope-validator", "halt-when-uncertain"],
"outputValidation": {
"enabled": true,
"rules": ["api_key_generic", "aws_access_key"],
"contentFilter": {
"deniedTopics": ["malicious code"]
}
}
}
With Tool Permissions
json
{
"enabled": true,
"toolPermissions": {
"bash": "ask",
"write": "allow",
"edit": "allow"
}
}
With Sandbox
json
{
"enabled": true,
"sandbox": {
"enabled": true,
"type": "docker",
"image": "node:18-slim"
}
}
With Canary Tokens
json
{
"enabled": true,
"canary": {
"enabled": true,
"prefix": "CATALOG:",
"tokenLength": 32
}
}

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
78
Repository forks
2
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/thearchitectit/agent-guardrails-template/docs-access/badge)](https://verified-skill.com/skills/thearchitectit/agent-guardrails-template/docs-access)

Something wrong with this skill or its page? Tell us.