zebbern/claude-code-guide

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!

4.6kStars on the repository
60Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

change-implementer

01

zebbern/claude-code-guide

Agent Claude Code

Use when requirements, an approved design, or a root cause are clear and one scoped, complete implementation is authorized. Do not use for unresolved exploration, product decisions, diagnosis-only work, or review-only requests.

4.6k 3d ago A 47 tokens original MIT

code-reviewer

02

zebbern/claude-code-guide

Agent Claude Code

Use proactively after an implementation or when an existing diff needs correctness, regression, concurrency, compatibility, and meaningful verification review. Do not use for implementation or a dedicated exploitability assessment.

4.6k 3d ago A 40 tokens original MIT

codebase-mapper

03

zebbern/claude-code-guide

Agent Claude Code

Use proactively when a task needs local repository structure, entry points, ownership, data flow, or change-surface mapping before a decision. Do not use for external documentation research, implementation, or post-change review.

4.6k 3d ago A 47 tokens original MIT

zebbern/claude-code-guide

Agent Claude Code

Use proactively when a decision depends on current official documentation, release notes, schemas, supported models, APIs, or version-specific behavior. Do not use when the primary work is tracing local code or implementing a change.

4.6k 3d ago A 49 tokens original MIT

root-cause-debugger

05

zebbern/claude-code-guide

Agent Claude Code

Use proactively when a failure must be reproduced, isolated, and causally explained before a fix is written. Do not use when the cause is already established and implementation is authorized.

4.6k 3d ago A 41 tokens original MIT

runtime-verifier

06

zebbern/claude-code-guide

Agent Claude Code

Use after a completed change when acceptance criteria must be exercised through the real user-facing, CLI, service, browser, filesystem, or integration boundary. Do not use to implement fixes or when the change is incomplete.

4.6k 3d ago A 46 tokens original MIT

security-reviewer

07

zebbern/claude-code-guide

Agent Claude Code

Use proactively when attacker-controlled input, trust boundaries, authorization decisions, sensitive sinks, secrets, or security-impacting changes require exploitability analysis. Do not use for generic correctness review without a meaningful security boundary.

4.6k 3d ago A 45 tokens original MIT

solution-architect

08

zebbern/claude-code-guide

Agent Claude Code

Use when established requirements and evidence leave multiple viable designs or cross-component boundaries that need explicit trade-offs before implementation. Do not use for a small specified fix or while the root cause is still unknown.

4.6k 3d ago A 43 tokens original MIT