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/anoopsg/agent_rules/manage-permissionsnpx skills add anoopsg/agent_rules --skill manage-permissionsgit clone --depth 1 https://github.com/anoopsg/agent_rulesWrote 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/anoopsg/agent_rules/manage-permissions)<a href="https://agentmods.dev/skills/anoopsg/agent_rules/manage-permissions"><img src="https://agentmods.dev/badge/skills/anoopsg/agent_rules/manage-permissions.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00706 |
| Opus 5 | $0.00020 | $0.00353 |
| Sonnet 5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
manage-permissions 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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Permissions & RBAC Management Skill
This skill defines the process for extending the RBAC (role-based access control) model and gating routes or UI by capability. See ADR-0014 for the full design rationale — this skill only covers the mechanics.
1. The Model
UserRole(lib/src/infrastructure/auth/models/user_role.dart): an enum of session roles (e.g.guest,standard).Permission(lib/src/infrastructure/auth/models/permission.dart): an enum of capabilities (e.g.settingsView,postsEdit). Routes and widgets declare aPermission, never aUserRoledirectly.kRolePermissions(lib/src/infrastructure/auth/models/role_permissions.dart): a single staticMap<UserRole, Set<Permission>>— the one source of truth for what each role can do.AppState.permissionsderives the current session's permission set fromkRolePermissions; every consumer reads through this, neverkRolePermissionsdirectly.
2. Step 1 — Add a New Permission
Add a member to the Permission enum:
enum Permission {
settingsView,
postsEdit,
// ...
reportsView,
}
3. Step 2 — Grant It to a Role
Update kRolePermissions:
const kRolePermissions = <UserRole, Set<Permission>>{
UserRole.guest: {},
UserRole.standard: {
Permission.settingsView,
Permission.postsEdit,
Permission.reportsView,
},
};
4. Step 3 — Gate a Route
Pass requiredPermission on the route's _AppRoute
definition (see manage-routes for the general route-adding
process):
final class _ReportsRoute extends _AppRoute {
const _ReportsRoute()
: super(
path: '/reports',
name: 'reports',
requiredPermission: Permission.reportsView,
);
@override
Widget build(_, _) => const ReportsPage();
}
PermissionGuard (a RouteGuard, priority 40) enforces this
automatically at navigation time — no further wiring needed.
5. Step 4 — Gate In-Place UI
For a widget that isn't a full route (e.g. hiding a button
rather than blocking navigation), use PermissionGate or the
PermissionCheck extension
(lib/src/shared/permission_gate.dart):
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.
- 5d ago First seen · 108 lines · 41 tokens per session scan A d290b0903e59
manage-permissions is a skill published in the GitHub repository anoopsg/agent_rules (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 706 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 2026-08-31.
Other skills, from other repositories
flutter-idioms
Flutter Riverpod 3, freezed, gorouter, const widgets, repository pattern.
browser-automation
Playwright browser automation via MCP. Covers E2E testing, UI review, web scraping, screenshot capture, and general browser interaction. MCP-first — CLI is fallback only.
go-idioms
Go stdlib, error wrapping, interfaces, goroutines, table-driven tests, gofumpt.
rust-idioms
Rust ownership, tokio, thiserror/anyhow, Clippy pedantic, unsafe, lifetimes.
typescript-idioms
TypeScript strict mode, type narrowing, Zod validation, vitest, ESLint flat config.
vue-idioms
Vue 3 Composition API, Pinia stores, composables, Vite, Vitest.