mcpbeat Sign in

Hook Scope Guide Skill for Claude

Select hook scope (plugin, project, global) by audience. Use when authoring a hook.

2k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
324
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/athola/claude-night-market --skill hook-scope-guide

The instruction itself

25 sections, as written by the author

Hook Scope Decision Guide

Overview

This skill helps you choose the right location for Claude Code hooks based on their purpose, audience, and persistence needs.

When NOT To Use

  • Writing the hook itself (use abstract:hook-authoring)
  • Scoring an existing hook (use abstract:hooks-eval)

Important: Auto-Loading Behavior

> hooks/hooks.json is automatically loaded by Claude Code when the plugin is enabled.

> Do NOT add "hooks": "./hooks/hooks.json" to your plugin.json - this causes duplicate load errors.

> The hooks field in plugin.json is only needed for additional hook files beyond the standard hooks/hooks.json.

The Three Scopes

| Scope | Location | Audience | Committed? | Persistence |

|-------|----------|----------|------------|-------------|

| Plugin | hooks/hooks.json in plugin | Plugin users | With plugin | When plugin enabled |

| Project | .claude/settings.json | Team members | Yes (repo) | Per project |

| Global | ~/.claude/settings.json | Only you | Never | All sessions |

Decision Framework

Question 1: Who needs this hook?

Only plugin users → Plugin hooks

  • Hook is part of plugin's core functionality
  • Users expect it when they enable your plugin
  • Example: A YAML plugin validates YAML syntax on edit

All team members on this project → Project hooks

  • Codebase-specific rules or protections
  • Team conventions that should be enforced
  • Example: Block modifications to /src/production/ configs

Only me, everywhere → Global hooks

  • Personal preferences or workflow optimizations
  • Cross-project utilities like logging
  • Example: Log all bash commands to personal audit trail

Question 2: Should this be version controlled?

Yes, as part of a distributable plugin → Plugin hooks

Yes, shared with team in repo → Project hooks

No, keep private → Global hooks

Question 3: What's the persistence requirement?

Only when my plugin is active → Plugin hooks

Always in this specific project → Project hooks

Always, in every project I work on → Global hooks

Scope Details

Plugin Hooks

Location: <plugin-root>/hooks/hooks.json

When to use:

  • The hook is intrinsic to your plugin's functionality
  • It should automatically activate when users enable your plugin
  • It only makes sense in the context of your plugin's features

Configuration:

{
  "PreToolUse": [
    {
      "matcher": "Read",
      "hooks": [{
        "type": "command",
        "command": "echo \"Plugin reading: $(jq -r '.tool_input.file_path')\" >> ${CLAUDE_PLUGIN_ROOT}/log.txt"
      }]
    }
  ]
}

> Note: Use string matchers ("Read") not object matchers ({"toolName": "Read"}).

Key features:

  • Use ${CLAUDE_PLUGIN_ROOT} for plugin-relative paths
  • Auto-merges when plugin is enabled
  • Deactivates when plugin is disabled

Examples:

  • Validation hook for a linting plugin
  • Auto-formatting hook for a code style plugin
  • Logging hook for a debugging plugin

Project Hooks

Location: .claude/settings.json (in project root)

When to use:

  • Enforcing team-wide policies
  • Protecting project-specific resources
  • Codebase conventions that should survive across team members
  • Rules that should be reviewed in PRs

Configuration:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [{
          "type": "command",
          "command": "cmd=$(jq -r '.tool_input.command // empty'); if [[ \"$cmd\" == *\"production\"* ]]; then echo 'BLOCKED: Production access requires approval'; exit 1; fi"
        }]
      }
    ]
  }
}

> Note: Use string matchers ("Bash") not object matchers.

Key features:

  • Committed to version control
  • Shared across all team members
  • Changes are visible in PRs (governance trail)
  • Project-specific, not personal

Examples:

  • Block modifications to production configs
  • Require test commands before completion
  • Warn about editing sensitive directories
  • Enforce project naming conventions

Global Hooks

Location: ~/.claude/settings.json

When to use:

  • Personal workflow preferences
  • Cross-project utilities
  • Organization-wide compliance you want everywhere
  • Private rules that shouldn't be shared

Configuration:

{
  "hooks": {
    "PreToolUse": [
      {
        "hooks": [{
          "type": "command",
          "command": "echo \"$(date): $(jq -r '.tool_name')\" >> ~/.claude/audit.log"
        }]
      }
    ]
  }
}

Key features:

  • Never committed to any repo
  • Applies to ALL Claude Code sessions
  • Personal to your user account
  • Survives across projects

Examples:

  • Personal audit logging
  • Cross-project safety rules
  • Custom notification integrations
  • Development environment preferences

Loading Order & Precedence

Claude Code loads settings in this priority (highest first):

  • Enterprise policies (organization-managed)
  • Command-line arguments (claude --flag)
  • Local project settings (.claude/settings.local.json)
  • Shared project settings (.claude/settings.json)
  • User settings (~/.claude/settings.json)

Important: Multiple hooks from different scopes can respond to the same event. When they do, all matching hooks execute in parallel.

Quick Reference: Scope Selection

Is this hook part of a plugin's core functionality?
├─ YES → Plugin hooks (hooks/hooks.json in plugin)
└─ NO ↓

Should all team members on this project have this hook?
├─ YES → Project hooks (.claude/settings.json)
└─ NO ↓

Should this hook apply to all my Claude sessions?
├─ YES → Global hooks (~/.claude/settings.json)
└─ NO → Reconsider if you need a hook at all

Security Considerations

Plugin hooks:

  • Audited as part of plugin installation
  • Users consent when enabling plugin
  • Scope limited to plugin's purpose

Project hooks:

  • Visible to all team members
  • Changes reviewed in PRs
  • Should reflect team consensus

Global hooks:

  • Execute with your credentials everywhere
  • Can affect all projects unexpectedly
  • Review security implications carefully
  • Test thoroughly before adding

Common Patterns by Scope

Plugin Hook Patterns

  • Validation: Check files match plugin's format
  • Auto-completion: Suggest plugin-specific completions
  • Logging: Track plugin-specific operations

Project Hook Patterns

  • Protection: Block dangerous operations on sensitive paths
  • Enforcement: Require tests, linting, or builds
  • Conventions: Warn about style or naming violations

Global Hook Patterns

  • Auditing: Log all operations for personal review
  • Safety: Universal dangerous command detection
  • Integration: Personal tool notifications

SessionStart Hook Enhancements (Claude Code 2.1.2+)

SessionStart hooks now receive additional input fields via stdin:

| Field | Type | Description |

|-------|------|-------------|

| session_id | string | Unique session identifier |

| source | enum | "startup" \| "resume" \| "clear" \| "compact" |

| agent_type | string | Agent name if --agent flag used, empty otherwise |

Agent-Aware Hooks

The agent_type field enables scope-appropriate context injection:

# Skip heavy context for review agents
input_data = json.loads(sys.stdin.read())
if input_data.get("agent_type") in ["code-reviewer", "quick-query"]:
    print(json.dumps({"hookSpecificOutput": {"additionalContext": "Minimal"}}))

This is particularly useful for:

  • Plugin hooks: Reduce overhead for lightweight agents
  • Project hooks: Skip governance for review-only agents
  • Global hooks: Customize logging verbosity per agent
  • abstract:hook-authoring - For hook rule syntax and patterns
  • abstract:validate-plugin - For validating plugin structure including hooks

References

Exit Criteria

  • [ ] A single scope (plugin / project / global) is selected and the rationale traces through at

least two of the three decision questions (audience, version control, persistence).

  • [ ] The selected scope's file location (hooks/hooks.json, .claude/settings.json, or

~/.claude/settings.json) is confirmed to exist or is created at the correct path.

  • [ ] Plugin hooks do not add "hooks": "./hooks/hooks.json" to plugin.json (duplicate-load

guard); this absence is verified before the hook is deployed.

  • [ ] Global hooks are flagged with a security note confirming they apply to all Claude sessions

on this machine.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take athola/hook-scope-guide from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.