Plugins

Graduated plugin-hook test agents — isolates hook resolution behavior (CLAUDE_PLUGIN_ROOT vs CLAUDE_PROJECT_DIR, frontmatter vs hooks.json) with canary-file reporting and hook-input-JSON dumping

Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns

from michelabboud/claude-code

from chrismcgraw60/parallel_plot

Create configurable hooks from markdown rule files

ユーザー定義ルールで Claude Code のアクションを警告・ブロック (グローバル/プロジェクト 2 階層、regex tool_matcher 対応)

Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.

Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns or writing explicit rules.

from jason-hchsieh/marketplace

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.

Rule engine with rate-limited warnings, stderr fix for #12446, and convention-based discovery

Python hooks that enforce git workflow rules: issue-first workflow, commit message format, branch protection, and auto-approval for file operations.

from jmagly/ai-writing-guide

from davepoon/buildwithclaude

Notify when Claude finishes working

Prompt for confirmation before destructive operations

from kawaz/claude-plugins

Notify on command failures and build errors

Notify when Claude is waiting for user input

Notify when operations exceed time threshold

Notify on session start and end

Composable safety and hygiene hooks — force-push guard, secret scanner, plugin/skill manifest validators, branch nudges, and dirty-tree stop check.

Declarative YAML hook rules compiled to native Claude Code hooks. Supports regex, script, and prompt mechanisms with build-time validation.

Adds alignment before implementation, evidence-based work review, PR explanations, clear writing, and shared settings. Requires Node.js 20 or newer.

The Hoplite knowledge-graph MCP server. Stub — under design.

The Hoplite authoring skills — glossary, spec, decision, notes, journal, todo, domain modeling — plus the frontmatter-validation hook and the locked specs they enforce.

Traduce el Excel de mediciones de cualquier arquitecto a una tabla estructurada estándar.

78 local Horosa (星阙) technique tools over MCP + the horosa-agent skill (clarify-before-call gate, export-snapshot reading). Requires the offline runtime: run `uv run horosa-skill install` inside the plugin's horosa-skill/ directory once.

Hospice referral-sales / community-liaison team — 6 agents (referral-development-strategist, hospice-eligibility-educator, referral-account-manager, admissions-conversion-coach, goals-of-care-conversation-coach, hospice-sales-compliance-advisor) for a hospice sales / community-education rep who grows admissions by developing referral sources (hospitals, SNFs, physician practices, ACOs): territory planning, educating clinicians on hospice eligibility (LCD decline criteria by diagnosis — the rep educates, the physician certifies), referral-partner reviews, the referral-to-admission funnel, the goals-of-care 'hospice conversation', and clearing every touch against the Anti-Kickback / HIPAA line. 6 skills, 6 commands, a 4-doc knowledge bank (6 decision trees + glossary + LCD + compliance references), 14 best-practices, scenarios, and a runnable funnel / census / benefit-period calculator. Employer-neutral; public practice + CMS rules. Requires ravenclaude-core@>=0.7.0.