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.
npx skills add vizra-ai/vizra-adk --skill vizra-tool-creationgit clone --depth 1 https://github.com/vizra-ai/vizra-adkWrote 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.
[](https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-tool-creation)<a href="https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-tool-creation"><img src="https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-tool-creation/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.
<a href="https://agentmods.dev/skills/vizra-ai/vizra-adk/vizra-tool-creation"><img src="https://agentmods.dev/badge/skills/vizra-ai/vizra-adk/vizra-tool-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.02728 |
| Opus 5 | $0.00015 | $0.01364 |
| Sonnet 5 | $0.00006 | $0.00546 |
| Haiku 4.5 | $0.00003 | $0.00273 |
Grade A, and why
Vizra ADK Tool Creation 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Vizra ADK Tools
Tools extend agent capabilities by allowing them to interact with databases, APIs, files, and external services.
Tool Class Structure
Every tool MUST implement ToolInterface:
<?php
namespace App\Tools;
use Vizra\VizraADK\Contracts\ToolInterface;
use Vizra\VizraADK\Agents\AgentContext;
class {{ ToolName }}Tool implements ToolInterface
{
/**
* Define the tool's schema for the LLM
*/
public function definition(): array
{
return [
'name' => '{{ tool_name }}',
'description' => '{{ What this tool does - be specific }}',
'parameters' => [
'type' => 'object',
'properties' => [
'param1' => [
'type' => 'string',
'description' => '{{ Parameter description }}'
],
'param2' => [
'type' => 'integer',
'description' => '{{ Parameter description }}'
],
],
'required' => ['param1'],
],
];
}
/**
* Execute the tool with given arguments
*/
public function execute(array $arguments, AgentContext $context): string
{
// Tool logic here
return json_encode([
'status' => 'success',
'data' => $result
]);
}
}
Key Rules
-
Naming Convention:
- Class name MUST end with
Tool - The
namein definition should be snake_case
- Class name MUST end with
-
Definition Requirements:
name: Unique identifier for the tooldescription: Clear description of what the tool does (LLM uses this to decide when to use the tool)parameters: JSON Schema format describing expected inputs
-
Return Format:
- Always return JSON-encoded strings
- Include status indicators for success/error
- Provide meaningful error messages
Parameter Types
'parameters' => [
'type' => 'object',
'properties' => [
// String parameter
'name' => [
'type' => 'string',
'description' => 'The user name'
],
// Integer parameter
'count' => [
'type' => 'integer',
'description' => 'Number of items'
],
// Boolean parameter
'active' => [
'type' => 'boolean',
'description' => 'Whether the item is active'
],
// Enum parameter
'status' => [
'type' => 'string',
'enum' => ['pending', 'approved', 'rejected'],
'description' => 'Current status'
],
// Array parameter
'tags' => [
'type' => 'array',
'items' => ['type' => 'string'],
'description' => 'List of tags'
],
// Object parameter
'metadata' => [
'type' => 'object',
'properties' => [
'key' => ['type' => 'string'],
'value' => ['type' => 'string']
],
'description' => 'Additional metadata'
],
],
'required' => ['name', 'count'],
]
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.
- 13d ago First seen · 465 lines · 29 tokens per session scan A 5c83ea204cf2
Vizra ADK Tool Creation is a skill published in the GitHub repository vizra-ai/vizra-adk (295 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 2,728 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 2026-08-30.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.