Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jrobelia/inventree-plugin-ai-toolkitnpx agentmods add skills/jrobelia/inventree-plugin-ai-toolkit/new-inventree-pluginWrote 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/jrobelia/inventree-plugin-ai-toolkit/new-inventree-plugin)<a href="https://agentmods.dev/skills/jrobelia/inventree-plugin-ai-toolkit/new-inventree-plugin"><img src="https://agentmods.dev/badge/skills/jrobelia/inventree-plugin-ai-toolkit/new-inventree-plugin/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/jrobelia/inventree-plugin-ai-toolkit/new-inventree-plugin"><img src="https://agentmods.dev/badge/skills/jrobelia/inventree-plugin-ai-toolkit/new-inventree-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.01928 |
| Opus 5 | $0.00022 | $0.00964 |
| Sonnet 5 | $0.00009 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade C, and why
new-inventree-plugin scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /workspace/plugins/<plugin-name>/.github/workflows How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New InvenTree Plugin Skill
Purpose: Agent-driven scaffolding for new InvenTree plugins
Overview
This skill guides an AI agent through creating a new InvenTree plugin from scratch. The agent first reaches a clear plan, then runs plugin-creator, explicitly opts out of CI, applies the toolkit's plugin-templates/ test scaffold, and verifies the result.
Prerequisites
Complete the initial setup in SETUP.md before using this skill. This includes:
- Docker Desktop installed and running
- VS Code with Dev Containers extension (or the CLI docker compose path)
- Devcontainer open and running
reference/plugin-creatorsubmodule initialized
For automated command execution (Docker exec), see SESSION-ONBOARDING.md.
Workflow
1. Plan the Plugin
Do not run plugin-creator until the plugin's purpose and shape are clear. If the user has not already produced a plan doc, invoke /wayfinder (or an equivalent planning mode) to produce one.
The plan doc must include enough information to answer every plugin-creator prompt:
- Plugin name (kebab-case)
- Human-readable name and description
- Author / license
- Required InvenTree mixins (e.g., EventMixin, NavigationMixin, UserInterfaceMixin, SettingsMixin)
- Frontend needs: panels, dashboard items, buttons, spotlight actions, etc.
- Whether the plugin is headless (no React frontend) or UI/hybrid (has a
frontend/package) - API endpoints and DRF serializers (if any)
- Database models and plugin settings (if any)
- Test fixtures or part IDs the E2E tests will need
Only proceed once the user confirms the plan is complete enough to scaffold.
2. Determine the Module Name
From the plan, determine the Python module name. This is usually the package_name produced by plugin-creator (the directory inside the plugin root that will contain __init__.py and core.py).
Use <MODULE_NAME> in all commands below.
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.
- 10d ago First seen · 211 lines · 43 tokens per session scan C d0883be7f249
new-inventree-plugin is a skill published in the GitHub repository jrobelia/inventree-plugin-ai-toolkit (1 stars, last pushed 23d ago), licensed MIT. It adds 43 tokens to every session and 1,928 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dotnet-testing-advanced-tunit-advanced
A guide for advanced TUnit testing in .NET. TUnit is a testing framework; the guide covers tests driven by data, dependency injection, integration tests, retries, time limits, and filtering.
dotnet-testing-autodata-xunit-integration
A guide for using AutoFixture, a .NET library that creates test data, with xUnit, a .NET testing framework. It explains attributes such as AutoData, InlineAutoData, and MemberAutoData for supplying values to parameterized tests.
dotnet-testing-autofixture-nsubstitute-integration
A .NET testing guide for using AutoFixture and NSubstitute to automatically create test data and substitute versions of dependencies.
dotnet-testing-bogus-fake-data
A guide to Bogus, a .NET library for generating realistic fake data such as names, addresses, phone numbers, emails, and product records. It shows how to define generation rules and create one or many records.
dotnet-testing-advanced-aspire-testing
A guide to testing .NET Aspire distributed applications, which are programs made of several coordinated services. It covers tests that run the real service setup through an AppHost, the project that describes how those services are arranged.
dotnet-testing-advanced
A guide that routes advanced .NET testing questions to the right specialist instructions. It covers API and integration tests, database and other container-based tests, microservices, .NET Aspire, and related testing tools.