guard-skills: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

by amElnagdy · Codex Skill · ★ 1.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Code Review

How to install guard-skills

npx skills add amElnagdy/guard-skills --list
npx skills add amElnagdy/guard-skills

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 72/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 13 tools we ran end to end on the same task for our Code Review page (2026-10-10).

Result: found 8 of 8 planted defects · 0 false alarms on 4 clean pull requests · 1.4 findings per pull request · 2 min · reviewed by Claude Opus 5.5

See every review → · See the whole test →

agent-skillsaiclaudeclaude-codecode-reviewcodexskills-shwoocommercewordpress

Quick Facts

Stars1,314
Forks142
CategoryCodex Skill
LicenseMIT
Quality Score72/100
Open Issues4
Last Updated2026-07-04
Created2026-06-06
Platformsclaude-code, codex
Est. Tokens~9k

About guard-skills

guard-skills Focused guard skills for coding agents: second-pass quality gates that catch the systematic failure modes of AI-generated code, tests, and docs before they ship. Best use: let your agent do the work, then invoke the relevant guard on the diff before you present, commit, or merge it.

Compatible Skills

These tools work well together with guard-skills for enhanced workflows:

  • canvas-mcp — semantic(0.24)+complementary+rare_topics+similar_pop+shared_platform (53%)
  • multi-agent-ralph-loop — semantic(0.25)+complementary+similar_pop+shared_platform (49%)
  • ai-agent-skills — semantic(0.24)+complementary+similar_pop+shared_platform (49%)
  • turbo — semantic(0.24)+complementary+similar_pop+shared_platform (49%)
  • DSkills — semantic(0.23)+complementary+similar_pop+shared_platform (48%)

guard-skills alternative? Top 6 similar tools

Looking for a guard-skills alternative? If you're comparing guard-skills with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agentsys by agent-sh · ⭐ 1.0k

    AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCod

  • mcp-linker by milisp · ⭐ 345

    Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c

  • claude-workflow-v2 by CloudAI-X · ⭐ 1.4k

    Universal Claude Code workflow plugin with agents, skills, hooks, and commands

  • claude-code-skills by levnikolaevich · ⭐ 592

    Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical founda

  • ai-workflow by nicepkg · ⭐ 291

    🚀 170+ pre-built skills for Claude Code, Cursor, Codex & 14+ AI tools. Stop re-teaching your AI the same thin

  • deepcontext-mcp by Wildcard-Official · ⭐ 277

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools