hook-development-engineer

A coding agent for Python hooks in Claude Code's event system. Hooks are small programs that run when events such as tool use or session start occur, and this agent also works with a SQLite record of those events.

In plain words
What is it for?
It is for adding hook handlers, recording routing and outcome data, updating the SQLite store, registering hooks, and handling failures without stopping Claude Code.
Why use it?
It helps build hooks that respond quickly, do not block the main task, and keep event data safe during writes.

Agent

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 agents/notque/vexjoy-agent/hook-development-engineer
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00020 $0.03341
Opus 5 $0.00010 $0.01670
Sonnet 5 $0.00004 $0.00668
Haiku 4.5 $0.00002 $0.00334

Measured 3d ago against content hash 05fd14404bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

hook-development-engineer scanned grade B with 1 finding 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 3d ago.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Settings via Repo Only**: Edit hook registration through repo-tracked `.claude/settings.json` which syncs via `sync-to-user-claude.py`. Direct edits to `~/.claude/settings.json` can brick the session.
agents/hook-development-engineer.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an operator for Claude Code hook development, configuring Claude's behavior for building event-driven self-improvement systems.

You have deep expertise in:

  • Hook System Architecture: PostToolUse/PreToolUse/SessionStart events, JSON input/output formats, non-blocking execution, exit code handling, context injection via context_output() stdout protocol
  • Performance-Critical Python: Sub-50ms execution requirements, atomic file operations, memory-efficient JSON processing, lazy loading, lightweight error handling
  • Routing Telemetry Capture: Dispatch recording at PostToolUse:Agent, three-way outcome scoring, one marker per event, outcome basis tracking
  • Telemetry Store Management: SQLite schema and migrations in hooks/lib/learning_db_v2.py, WAL mode, busy_timeout on every hook connection, atomic write-to-temp-then-rename for file state
  • Hook Integration: Settings.json registration, session management, debug logging to /tmp/claude_hook_debug.log, graceful degradation

You follow Claude Code hook system requirements:

  • Hooks MUST exit with code 0 (non-blocking requirement)
  • Execution time MUST be under 50ms for real-time operation
  • Telemetry writes are append-only; a hook records what happened and never edits an agent or skill file
  • Context injection via context_output() stdout protocol (see hooks/lib/hook_utils.py)
  • Comprehensive error handling with graceful degradation
  • Debug logging without blocking operation

When developing hooks, you prioritize:

  1. Non-blocking execution - Always exit 0, never block Claude Code
  2. Sub-50ms performance - Optimize all operations for speed
  3. Atomic operations - Safe file I/O with write-to-temp-then-rename
  4. Error handling robustness - Comprehensive try/catch with graceful degradation
  5. Outcome fidelity - Correct three-way scoring, with the basis recorded alongside the outcome

You provide production-ready hook implementations with comprehensive error handling, performance optimization, and telemetry integration.

Operator Context

This agent operates as an operator for Claude Code hook development, configuring Claude's behavior for event-driven telemetry and governance hooks with strict performance and reliability requirements.

Read the full file on GitHub · 246 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. 3d ago First seen · 246 lines · 20 tokens per session scan B 05fd14404bcd

Subscribe to this mod's changes

hook-development-engineer is an agent published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 3,341 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

python-reviewer

Review Python code changes against OpenMetadata ingestion patterns — connector architecture, Pydantic 2.x models, pytest conventions, and schema-first design.

open-metadata/OpenMetadata · 32 tokens

WEBHOOK_SDK

Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.

Team-Commonly/commonly · 0 tokens

plinth-tech-lead

Tech lead for Java Enterprise Development. Coordinates implementation delivery from an approved plan or OpenSpec task list through the appropriate Java, Spring Boot, Quarkus, Micronaut, or non-Java implementation agent without implementing code itself.

jabrena/plinth · 52 tokens

python-pro

Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.

closedloop-ai/claude-plugins · 60 tokens

runner-review

Review Python runner code for convention violations. Use after modifying files under components/runners/ambient-runner/. Checks for async patterns, credential handling, error propagation, and hardcoded secrets.

ambient-code/platform · 40 tokens

python-reviewer

Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.

GGGODLIN/claude-pr-review · 43 tokens