ajsai47

65 mods across 2 repositories, 313 stars between them.

help

49

ajsai47/holyclaude

Command

Get help with the hookify plugin.

11 5mo ago D 7 tokens original MIT

list

50

ajsai47/holyclaude

Command

List all configured hookify rules.

11 5mo ago A 6 tokens copy · 100% MIT

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

11 5mo ago D 51 tokens copy · 100% MIT

ajsai47/holyclaude

Plugin Claude Code

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style).

11 5mo ago A tokens not measured original MIT

Agent Development

53

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…

11 5mo ago A 80 tokens copy · 91% MIT

Command Development

54

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash…

11 5mo ago A 99 tokens copy · 100% MIT

Hook Development

55

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDEPLUGINROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop…

11 5mo ago A 117 tokens copy · 100% MIT

MCP Integration

56

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDEPLUGINROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive…

11 5mo ago B 97 tokens copy · 100% MIT

Plugin Settings

57

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md…

11 5mo ago B 81 tokens copy · 100% MIT

Plugin Structure

58

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDEPLUGINROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest…

11 5mo ago A 92 tokens copy · 100% MIT

Skill Development

59

ajsai47/holyclaude

Skill Claude CodeCodex

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

11 5mo ago A 63 tokens copy · 100% MIT

pr-review-toolkit

60

ajsai47/holyclaude

Plugin Claude Code

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification.

11 5mo ago A tokens not measured copy · 100% MIT

ralph-wiggum

61

ajsai47/holyclaude

Plugin Claude Code

Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

11 5mo ago A tokens not measured copy · 100% MIT

security-guidance

62

ajsai47/holyclaude

Plugin Claude Code

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns.

11 5mo ago A tokens not measured original MIT

do

63

ajsai47/holyclaude

Skill Claude CodeCodex

Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.

11 5mo ago A 32 tokens original MIT

make-plan

64

ajsai47/holyclaude

Skill Claude CodeCodex

Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.

11 5mo ago A 35 tokens original MIT

mem-search

65

ajsai47/holyclaude

Skill Claude CodeCodex

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

11 5mo ago A 42 tokens original MIT