KbWen/agentic-os

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

149Stars on the repository
55Mods indexed here, across every type
8d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

api-design

01

KbWen/agentic-os

Skill Claude CodeCodex

Design or review REST/GraphQL APIs when endpoints or contracts change.

149 8d ago A 17 tokens original MIT

auth-security

02

KbWen/agentic-os

Skill Claude CodeCodex

Secure authentication and authorization when credentials, sessions, roles, or permissions change.

149 8d ago A 18 tokens original MIT

database-design

03

KbWen/agentic-os

Skill Claude CodeCodex

Design schemas and migrations when persistent data structures change.

149 8d ago A 13 tokens original MIT

KbWen/agentic-os

Skill Claude CodeCodex

Evaluate when to dispatch parallel agents; use a 4-step pattern to split, coordinate, and integrate results.

149 8d ago A 29 tokens original MIT

doc-lookup

05

KbWen/agentic-os

Skill Claude CodeCodex

Check official docs when framework APIs or configuration may be version-sensitive.

149 8d ago B 17 tokens original MIT

frontend-patterns

06

KbWen/agentic-os

Skill Claude CodeCodex

Apply frontend conventions when components, pages, forms, or client state change.

149 8d ago A 19 tokens original MIT

karpathy-principles

07

KbWen/agentic-os

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.

149 8d ago A 34 tokens original MIT

KbWen/agentic-os

Skill Claude CodeCodex

Pre-ship observability readiness checklist — ensures errors reach production monitoring, not just debug consoles.

149 8d ago A 23 tokens original MIT

KbWen/agentic-os

Skill Claude CodeCodex

Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.

149 8d ago A 50 tokens original MIT

KbWen/agentic-os

Skill Claude CodeCodex

Decompose tasks via subagent collaboration; define interface contracts and integration checkpoints.

149 8d ago A 20 tokens original MIT

KbWen/agentic-os

Skill Claude CodeCodex

Use 4-phase root cause analysis (Observe, Hypothesize, Verify, Fix); avoid unverified patches.

149 8d ago A 28 tokens original MIT

KbWen/agentic-os

Skill Claude CodeCodex

Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.

149 8d ago A 23 tokens original MIT

using-git-worktrees

13

KbWen/agentic-os

Skill Claude CodeCodex

Use Git worktrees to create parallel working directories safely; avoid branch-switch contamination.

149 8d ago A 22 tokens original MIT