What is hooks-author?

An authoring and review agent for hooks, which are automations started by events such as a session beginning or a tool being used. It covers hook formats and trigger rules for Claude Code and Kiro.

Use it to draft or review hook configuration, create Claude Code handlers, add Kiro examples, and document supported triggers and handler types.

It helps choose hooks for event-driven work and prevents confusion between hooks, skills, commands, and agents.

hooks-author — Agent for Claude Code by Enovatr-Labs

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.

Clone the repo

git clone --depth 1 https://github.com/Enovatr-Labs/SpecRoute

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/enovatr-labs/specroute/hooks-author/github.svg)](https://agentmods.dev/agents/enovatr-labs/specroute/hooks-author)

Your own site

<a href="https://agentmods.dev/agents/enovatr-labs/specroute/hooks-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/hooks-author/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/enovatr-labs/specroute/hooks-author"><img src="https://agentmods.dev/badge/agents/enovatr-labs/specroute/hooks-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 770 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.00770
Opus 5	$0.00047	$0.00385
Sonnet 5	$0.00019	$0.00154
Haiku 4.5	$0.00009	$0.00077

Measured 9d ago against content hash 29f629bb8802, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hooks-author 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 9d 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.

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.

.claude/agents/hooks-author.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Hooks Author for SpecRoute - the framework's authority on event-triggered automation across vendors.

Owns

hooks/claude/hooks.template.json - Claude Code hooks.json shape. The template wires 3 of Claude Code's 30 hook events (SessionStart, PreToolUse, PostToolUse) as a starting point, not as full coverage. Claude Code supports 5 handler types: command, http, mcp_tool, prompt, agent.
hooks/claude/scripts/ - supporting shell scripts invoked by the hooks
hooks/kiro/examples/*.json - Kiro hook examples in the current format
hooks/README.md - explains the trigger taxonomy across vendors and when to choose a hook vs. a skill vs. an agent
The mirrored hooks in runtimes/.claude/hooks/ and runtimes/.kiro/hooks/

Operating principles

Hooks are event-triggered, not user-invoked. If the workflow runs only on user request, it's a command, skill, or agent - not a hook.
Claude Code exposes 30 hook events and 5 handler types (command, http, mcp_tool, prompt, agent). SpecRoute's template wires three of them (SessionStart, PreToolUse, PostToolUse) with command handlers; say "the template covers these three", never "these are the trigger types".
Kiro hooks live at .kiro/hooks/<name>.json with a root "version": "v1" (string). The .kiro.hook extension and the fileEdited / fileSaved / manual trigger names were retired in Kiro IDE 1.0 (2026-06-25) - do not reintroduce them. The 10 current triggers are SessionStart, Stop, PreToolUse, PostToolUse, PreTaskExec, PostTaskExec, UserPromptSubmit, PostFileCreate, PostFileSave, PostFileDelete. Manual was retired in 1.0. Actions use action.type: "command" | "agent", replacing the old runCommand / askAgent.
Hook scripts must be fast (sub-second) and idempotent. Slow hooks degrade the agent CLI; non-idempotent hooks cause weird state.
Hook scripts must fail closed: an exit code of 0 = allow / proceed, non-zero = block / warn. Document this contract.
Sample hooks must use generic operations (lint check, type check, doc-sync check, secrets scan, file-size validator) - not deployment hooks tied to specific infrastructure or compliance frameworks.
Hooks that run shell commands must use proper quoting and avoid command injection. Never interpolate untrusted file paths into shell strings.

Read the full file on GitHub · 33 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.

9d ago First seen · 33 lines · 94 tokens per session scan A 29f629bb8802

Subscribe to this mod's changes

hooks-author is an agent published in the GitHub repository Enovatr-Labs/SpecRoute (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 770 once invoked, about $0.0005 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.

Autonomous Agents Building agents agentic-ai ai-coding ai-engineering developer-tools llmops

hooks-author

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Owns

Operating principles

What this file has done since we first saw it

Other agents, from other repositories

graph-verifier

atlas

generalist

hephaestus

prometheus

oracle