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 fpindej/netrock --skill add-permissiongit clone --depth 1 https://github.com/fpindej/netrockWrote 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/fpindej/netrock/add-permission)<a href="https://agentmods.dev/skills/fpindej/netrock/add-permission"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/add-permission/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/fpindej/netrock/add-permission"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/add-permission.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 | $0.00008 | $0.00402 |
| Opus 5 | $0.00004 | $0.00201 |
| Sonnet 5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
add-permission scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Adds a permission constant across backend and frontend.
Steps
Backend:
- Add
public const stringfield to the appropriate nested class insrc/backend/MyProject.Application/Identity/Constants/AppPermissions.cs:public static class Orders { public const string View = "orders.view"; public const string Manage = "orders.manage"; }AppPermissions.Alldiscovers permissions via reflection - no manual registration needed. - Add
[RequirePermission(AppPermissions.Orders.View)]to the relevant controller actions - (Optional) Add the permission to a role's
DefaultPermissionsinAppRoles.Definitions(src/backend/MyProject.Application/Identity/Constants/AppRoles.cs) - the startup seeder applies it additively - Verify:
dotnet build src/backend/MyProject.slnx
Frontend:
- Add matching constants to
src/frontend/src/lib/utils/permissions.ts:Orders: { View: 'orders.view', Manage: 'orders.manage', }, - Use in components:
hasPermission(user, Permissions.Orders.View) - If adding a new admin page: register it in
adminRoutesin$lib/config/routes.ts(path + permission), then guard in+page.server.ts:if (!hasPermission(user, adminRoutes.orders.permission)) throw redirect(303, routes.dashboard); - If adding a sidebar nav item: use
adminRoutes.orders.pathand.permissionfor the nav item inAppSidebar.svelte- items are filtered per-permission, not as a group - Verify:
cd src/frontend && pnpm run test && pnpm run format && pnpm run lint && pnpm run check
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.
- 9d ago First seen · 41 lines · 8 tokens per session scan A af9c5b050fd2
add-permission is a skill published in the GitHub repository fpindej/netrock (232 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 402 once invoked, about $0.0000 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
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
orchardcore-crestapps-resources
Skill for CrestApps resource-management extensions in Orchard Core. Covers the shared registered scripts and stylesheets, local asset and CDN fallback behavior, resource names, dependency consumption, and safe Razor registration. Use this skill when requests mention CrestApps shared resources, Orchard Core resource…
api-design
Guidelines for RESTful API design, endpoint naming conventions, and standardizing JSON responses.
python
Enforces FastAPI, Dependency Injection, and general Python coding standards based on the repository structure.
react
Guidelines for the React frontend, TanStack ecosystem, and React 19 standards. Use when modifying the UI.
react-testing
Frontend testing standards using Vitest, React Testing Library, and Playwright. Use when writing UI tests.