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 agentmods add skills/odradekai/bundles-forge/testingnpx skills add OdradekAI/bundles-forge --skill testinggit clone --depth 1 https://github.com/OdradekAI/bundles-forgeWhat 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 | $0.00032 | $0.01687 |
| Opus 5 | $0.00016 | $0.00843 |
| Sonnet 5 | $0.00006 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00169 |
Grade A, and why
testing 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 2d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Bundle-Plugins
Overview
Dynamic verification of a bundle-plugin project: install it locally, confirm components are discoverable, validate hooks fire correctly, and run cross-platform smoke tests. Complements bundles-forge:auditing (static analysis) with runtime validation.
Core principle: Audit tells you if the structure is correct; testing tells you if it actually works.
Skill type: Flexible — adapt the test scope based on target platforms and project maturity.
Announce at start: "I'm using the testing skill to verify this plugin works correctly."
Step 1: Resolve Input & Detect Scope
Input Normalization
The target must be a local bundle-plugin project (has package.json + skills/). Remote URLs and archives are not supported — testing requires a local working directory.
Scope Detection
| Target | Mode |
|---|---|
| Project root with multiple platforms | Full testing — all 5 test phases |
| Project root with single platform | Platform testing — phases 1-4 for the target platform |
| Single skill directory | Skill-only testing — phase 3 (component discovery) only |
Phase 1: Local Test Environment
Generate a temporary dev-marketplace for local installation testing.
For Claude Code
- Create
../dev-marketplace/adjacent to the project directory - Generate
.claude-plugin/marketplace.jsonpointing to the project:
{
"name": "<project-name>-dev",
"owner": { "name": "dev" },
"plugins": [
{
"name": "<project-name>",
"source": "../<project-directory-name>"
}
]
}
- Instruct the user:
Dev marketplace created at ../dev-marketplace/
To install locally:
/plugin marketplace add ./dev-marketplace
/plugin install <project-name>@<project-name>-dev
To reload after changes:
/plugin marketplace update <project-name>-dev
To clean up when done:
/plugin marketplace remove <project-name>-dev
For Cursor
Cursor plugins are installed from local paths directly:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 244 lines · 32 tokens per session scan A f602255ba8b6
testing is a skill published in the GitHub repository OdradekAI/bundles-forge (230 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,687 once invoked, about $0.0002 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
uikit-expert
Write, review, or improve UIKit code following best practices for view controller lifecycle, Auto Layout, collection views, navigation, animation, memory management, and modern iOS 18–26 APIs. Use when building new UIKit features, refactoring existing views or view controllers, reviewing code quality, adopting modern…
add-ai-protection
Deprecated: use the arcjet skill instead. Adds security protection to AI/LLM endpoints and non-HTTP code paths — prompt injection detection, PII blocking, and token budget rate limiting.
add-request-protection
Deprecated: use the arcjet skill instead. Adds security protection to a server-side route or endpoint — rate limiting, bot detection, email validation, and abuse prevention.
add-guard-protection
Deprecated: use the arcjet skill instead. Adds Arcjet Guard protection to AI agent tool calls, background jobs, queue workers, and other non-HTTP code paths.
arcjet
Add Arcjet security protection to any code path – HTTP route handlers, API endpoints, AI agent tool calls, MCP servers, background jobs, and queue workers. Covers rate limiting, bot detection, email validation, prompt injection detection, sensitive information blocking (including Rampart NER), content moderation…
protect-route
Deprecated: use the arcjet skill instead. Adds security protection to a server-side route or endpoint — rate limiting, bot detection, email validation, and abuse prevention.