Developing Internal Hooks

Developing Internal Hooks is a skill for Claude Code from RudyCity/superagent. It costs 28 tokens per session (1,646 once invoked), scanned A, original, MIT.

Instructions for creating project-specific extensions in an internal-hooks/ folder, including custom tools, terminal shortcuts, event-triggered scripts, and instruction bundles for agents.

In plain words
What is it for?
It is for building slash commands, lifecycle hooks that run before or after actions, custom agent tools, and project-local skills.
Why use it?
It lets a project add its own automation and agent behavior without changing the main application.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit It is for building slash commands, lifecycle hooks that run before or after actions, custom agent tools, and project-local skills.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rudycity/superagent/internal-hooks
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.

Any agent
npx skills add RudyCity/superagent --skill internal-hooks
Clone the repo
git clone --depth 1 https://github.com/RudyCity/superagent

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.

agentmods badge for Developing Internal Hooks

README.md
[![agentmods](https://agentmods.dev/badge/skills/rudycity/superagent/internal-hooks.svg)](https://agentmods.dev/skills/rudycity/superagent/internal-hooks)
Your own site
<a href="https://agentmods.dev/skills/rudycity/superagent/internal-hooks"><img src="https://agentmods.dev/badge/skills/rudycity/superagent/internal-hooks.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,646 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 122
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00028 $0.01646
Opus 5 $0.00014 $0.00823
Sonnet 5 $0.00006 $0.00329
Haiku 4.5 $0.00003 $0.00165

Measured 4d ago against content hash 856854e7d503, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Developing Internal Hooks 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 4d 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.

.agents/skills/internal-hooks/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developing Internal Hooks

Overview

Internal Hooks are custom user-defined scripts placed in subdirectories under internal-hooks/ at the root of the project. They are loaded dynamically at startup and allow extending Superagent's functionality in four powerful ways:

  1. AI Agent Tools: Dynamic custom tools available for AI agent execution.
  2. Custom Slash Commands: Custom command shortcuts available directly in the terminal CLI interface (e.g. /my-command).
  3. Event Hooks: Event-driven hooks executed during critical lifecycle points (e.g. pre-tool, post-tool, pre-command, post-command).
  4. Dynamic Skills: Custom agent instruction bundles (skills/<skill_name>/SKILL.md) packaged directly inside your hook folder.

Hook File Structure

Every hook must be placed in a subdirectory: internal-hooks/<hook_name>/. The structure MUST contain the following:

internal-hooks/<hook_name>/
├── hook.json             # Root schema mapping tools, slash commands, and event hooks
├── package.json          # Dependency and script management
├── index.js              # Entrypoint script executing logic
├── test-payload.json     # Stdin mock argument payload for local dev loop testing
├── README.md             # [Mandatory] Hook documentation
├── CHANGELOG.md          # [Mandatory] Hook release notes
└── skills/               # [Optional] Dynamic agent skills directory
    └── <my-custom-skill>/
        └── SKILL.md      # Skill markdown documentation for agent instruction

Mandatory Setup Requirements

All internal hooks are strictly required to have:

  1. README.md: Clear documentation explaining the hook's features, input arguments, environment variables, outputs, and how it behaves.
  2. CHANGELOG.md: A semantic versioning changelog following the Keep a Changelog format, tracking all versions, improvements, bug fixes, and breaking changes.
  3. Git Initialization: The hook subdirectory must be initialized as its own local Git repository (git init). This is done automatically by /ih init <hook_name>, which scaffolds the mandatory files and configures git.

Read the full file on GitHub · 151 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. 4d ago First seen · 151 lines · 28 tokens per session scan A 856854e7d503

Subscribe to this mod's changes

Developing Internal Hooks is a skill published in the GitHub repository RudyCity/superagent (21 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,646 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 2026-09-03.