visionclaw

visionclaw is a skill for Claude Code from Huskyauto/VisionClaw-Agent-Public-Release. It costs 0 tokens per session (3,585 once invoked), scanned A, original, MIT.

Instructions for using VisionClaw, a hosted platform with specialised AI agents, tools, skills, and models that can perform delegated work.

In plain words
What is it for?
Use it for tasks such as comparing products, creating documents or financial models, running overnight research, or coordinating several kinds of work.
Why use it?
They provide a way to send larger research, document-production, operations, or multi-step tasks to that hosted platform from a coding agent.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Part of the visionclaw-agent plugin — 1 skill, 3 commands, 1 MCP server shipped together

Good fit Use it for tasks such as comparing products, creating documents or financial models, running overnight research, or coordinating several kinds of work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huskyauto/visionclaw-agent-public-release/visionclaw
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 Huskyauto/VisionClaw-Agent-Public-Release --skill visionclaw
Clone the repo
git clone --depth 1 https://github.com/Huskyauto/VisionClaw-Agent-Public-Release

Made for: Claude Code.

Or install visionclaw-agent, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

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 visionclaw

README.md
[![agentmods](https://agentmods.dev/badge/skills/huskyauto/visionclaw-agent-public-release/visionclaw/github.svg)](https://agentmods.dev/skills/huskyauto/visionclaw-agent-public-release/visionclaw)
Your own site
<a href="https://agentmods.dev/skills/huskyauto/visionclaw-agent-public-release/visionclaw"><img src="https://agentmods.dev/badge/skills/huskyauto/visionclaw-agent-public-release/visionclaw/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.

agentmods 80×15 button for visionclaw

Your own site · 80×15
<a href="https://agentmods.dev/skills/huskyauto/visionclaw-agent-public-release/visionclaw"><img src="https://agentmods.dev/badge/skills/huskyauto/visionclaw-agent-public-release/visionclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 2 findings, 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 Data Exfiltration · line 88
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 291
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00000 $0.03585
Opus 5 $0.00000 $0.01792
Sonnet 5 $0.00000 $0.00717
Haiku 4.5 $0.00000 $0.00359

Measured 10d ago against content hash 056f16d8c1a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

visionclaw scanned grade A 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://agenticcorporation.net/api/v1
claude-skill/visionclaw/SKILL.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VisionClaw Skill (for Claude Code, Cursor, Gemini CLI, Codex)

Hire an AI corporation, not another chatbot.

VisionClaw is a hosted multi-tenant agentic platform — 16 specialized agents, 226+ tools, 62+ skills, 37+ AI models. This skill teaches your coding agent how to delegate research, document production, and operations work to it from inside your IDE.

Hosted at: https://agenticcorporation.net Discovery: GET /api/v1 (returns the live contract) Source / fork it: https://github.com/Huskyauto/VisionClaw-Agent-Public-Release License: Apache 2.0 · v1.0 shipped Apr 21, 2026


When to invoke this skill

Use /visionclaw whenever the user wants:

  • Research at scale — "Research competitor pricing for 5 SaaS tools and build me a comparison spreadsheet."
  • Document production — pitch decks, styled PDFs, financial models, legal contracts, marketing campaigns.
  • Long-running ops — overnight research with a delivery summary, scheduled reports, monitoring with alerts.
  • Multi-step deliverables — anything that would normally need 3+ different specialists (research → analysis → write-up → format → deliver).
  • Wellness coaching ([Your Product]) — wellness-coaching support, wellness accountability, mood tracking conversations.

If the user wants to write code in their own repo, stay with the IDE agent. Hand off to VisionClaw only when the work is agentic operations (multi-agent, multi-tool, deliverable-oriented).


Authentication

The user needs a VisionClaw account at https://agenticcorporation.net. After login they generate an API key from Settings → Security → Public API Keys and provide it to you as the env var VISIONCLAW_API_KEY. Keys begin with vc_ and are shown exactly once.

If VISIONCLAW_API_KEY is missing, ask the user to set it before proceeding. Never invent a key.

Scopes (selected at key creation):

  • chat — required to dispatch tasks and send messages
  • read — required to list agents and poll conversation status
  • tools — direct tool invocation (browser, research)
  • admin — full access including key management

Read the full file on GitHub · 331 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. 10d ago First seen · 331 lines · 0 tokens per session scan A 056f16d8c1a9

Subscribe to this mod's changes

visionclaw is a skill published in the GitHub repository Huskyauto/VisionClaw-Agent-Public-Release (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,585 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

autogpt-agents

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

davila7/claude-code-templates · 39 tokens

openacme-platform

How OpenAcme is laid out — data dir, agents, skills, MCP servers, tasks, memory, the peer-notes convention. Read this when the user asks you to manage their workforce, set up an agent, install a skill, configure an MCP server, or explain how the platform works.

sandydasari/openacme · 66 tokens

coding-conventions

Workforce coding conventions — read existing patterns, prefer narrow types, leave the surface area smaller than you found it.

sandydasari/openacme · 27 tokens

cc-autopilot

Run cc-autopilot, a perpetual autonomous AUDIT/GENERATE→TRIAGE→BATCH→FIX→VERIFY→REVIEW→COMMIT loop that holds every change to a configured quality bar through a judge panel. Its fixers each own a file-disjoint slice of the tree so no two can ever touch the same file, and nothing unverified reaches git. Works on a web…

gbotev1/cc-autopilot · 155 tokens

atelier

Operate the Atelier software factory (the ADW engine stamped into this repo's adws/). Use when the user says /atelier, wants to create / run / update an ADW or workflow, manage the agent roster in sssf.config.yaml, keep the engine current, or observe running agent workflows. Keywords - atelier, software factory, ADW…

duanecilliers/atelier · 87 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens