hooks-creator

A guide for creating Gemini CLI hooks, which are scripts that respond to events in the command-line coding agent.

In plain words
What is it for?
Use it to build hooks that block tools, add context, or record activity using Bash or Node.js.
Why use it?
It helps avoid broken hook output and unsafe handling of command data.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/matrixfounder/agentic-development/hooks-creator
Any agent
npx skills add MatrixFounder/Agentic-development --skill hooks-creator
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.01335
Opus 5 $0.00012 $0.00668
Sonnet 5 $0.00005 $0.00267
Haiku 4.5 $0.00002 $0.00134

Measured 2d ago against content hash 809e9051c407, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hooks-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (examples/inject_context.sh, examples/log_tools.sh, examples/security_gate.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agent/skills/hooks-creator/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hooks Creator

Purpose: Create robust, secure, and compliant Gemini CLI hooks that intercept and customize the agent's lifecycle (e.g., blocking tools, injecting context, logging).

[!WARNING] SECURITY CRITICAL:

  • Strict JSON: Printing to stdout breaks the CLI. Use stderr for logs.
  • Injection Risks: BASH hooks MUST use jq. Never use grep on raw input.
  • Dependency Checks: Scripts MUST fail gracefully (exit 2) if deps like jq are missing.

1. Red Flags (Anti-Rationalization)

STOP and READ THIS if you are thinking:

  • "I'll use grep to parse JSON in Bash because it's faster" -> WRONG. This is a security vulnerability. You MUST use jq.
  • "I'll just print a debug message to stdout" -> WRONG. This breaks JSON parsing. ALL logs must go to stderr.
  • "I can skip the dependency check" -> WRONG. Scripts will fail silently. functionality. Always check for jq or node modules.
  • "I'll use exit 1 for a denial" -> WRONG. Use exit 0 with {"decision": "deny"} for structured feedback, or exit 2 for system errors.

2. Capabilities

  • Generate Bash hooks for simple logic (using jq).
  • Generate Node.js hooks for complex logic or heavy JSON processing.
  • Configure settings.json with correct matchers and event types.
  • Validate security and performance best practices.

3. Instruction Protocol

Phase 1: Analyze & Clarify

  1. Identify the Event: Map user intent to the correct Life Cycle Event.
    • Example: "Stop me from committing secrets" -> BeforeTool (triggered on write_file).
    • Example: "Add git history to context" -> BeforeAgent (or SessionStart).
    • Example: "Add git history to context" -> BeforeAgent (or SessionStart).
  2. Analyize Clarity (Fast Path):
    • Clear Request: If the user provides specific intent (e.g., "Block 'rm' commands"), SKIP clarification and proceed to implementation.
    • Ambiguous Request: If vague (e.g., "Make it safer"), ask ONE clarifying question: "Do you want to block specific tools or scan content?"
  3. Select Implementation:
    • Bash: For simple checks (grepping specific patterns, file existence).
    • Node.js: For logic requiring array manipulation, complex JSON, or async calls.

Read the full file on GitHub · 104 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 104 lines · 24 tokens per session scan A 809e9051c407

Subscribe to this mod's changes

hooks-creator is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,335 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

add-tests

Generates tests for existing code. Analyzes the target function, method, or class to identify the happy path, error cases, and edge cases, then writes test cases following the project's testing framework and naming conventions. Invoked when the user asks to add tests, write tests, cover code, or increase coverage.

soulcodex/agentic · 67 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens

nunit-api-design

Use when adding or modifying public API surface in NUnit — new or changed constraints, attributes, assertions, helpers, or any type/member visibility change. Covers the conventions NUnit maintainers enforce for types that ship to consumers of the framework.

nunit/nunit · 51 tokens

review-offered-task

Review a task that has been offered to you and decide whether to accept or reject it.

desplega-ai/agent-swarm · 22 tokens

company-hiring-intelligence

Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…

tinyfish-io/tinyfish-cookbook · 169 tokens

Swift Performance Optimization Skill

Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…

termio-sh/termio · 68 tokens