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 ski043/kinde-agent-skills --skill kinde-authorizationgit clone --depth 1 https://github.com/ski043/kinde-agent-skillsWrote 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/ski043/kinde-agent-skills/kinde-authorization)<a href="https://agentmods.dev/skills/ski043/kinde-agent-skills/kinde-authorization"><img src="https://agentmods.dev/badge/skills/ski043/kinde-agent-skills/kinde-authorization/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/ski043/kinde-agent-skills/kinde-authorization"><img src="https://agentmods.dev/badge/skills/ski043/kinde-agent-skills/kinde-authorization.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 | $0.00068 | $0.02274 |
| Opus 5 | $0.00034 | $0.01137 |
| Sonnet 5 | $0.00014 | $0.00455 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
kinde-authorization 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kinde Authorization
Consumes a tenant contract from kinde-b2b. Produces an authorization contract: the permission catalog, role matrix, assignment matrix, and enforcement matrix for that tenant. Application and API decisions target permission keys, not role names.
Stance
Treat the run as design-only until the user authorizes implementation. Catalog writes are business-wide; plan them before mutating a shared business. Actively invoke the loaded framework adapter for framework syntax; absent adapter blocks implementation. Dated sources and official conflicts live in REFERENCES.md.
Generic JWT, tenant-binding, missing-organization, machine-credential, and plane-setup rules stay in kinde-b2b. This skill owns catalog, assignment, defaults, claim freshness, and permission-key enforcement.
Guardrails
- Permission keys. Server decisions use verified permission keys for the active organization. Roles are a management grouping.
- Shared catalog. Role and permission definitions are business-level. A write in a non-production environment is the same catalog in production.
- Membership first. Roles and permissions assign only to a user who already belongs to that organization.
- MCP writes stop at create. Management MCP may create roles and permissions and read selected relationships. It does not attach permissions to roles or assign roles or permissions to users. Broader writes use dashboard or Management API. Details: PLANES.md.
- Separate mechanisms. User permission keys, machine scopes, feature flags, and billing entitlements are different. Invoke the owning skill for flags or billing; an unavailable owner blocks that decision branch. Details: ENFORCEMENT.md.
Read map
- CATALOG.md: keys, roles as groupings, environment sharing, blast radius. Read in step 3.
- PLANES.md: catalog create, attach, assign, defaults, verified Management API table, import shapes. Read in steps 4–5.
- ENFORCEMENT.md: audience, claims, freshness,
scopevsscp, null-safe server checks. Read in steps 6–7. - SYSTEM.md: verified portal, billing, member, and API-key system permissions. Read when those keys appear.
- REFERENCES.md: dated sources and conflicts. Read before a product claim not already recorded, or when official pages disagree.
What ships with it
5 files 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.
- 9d ago First seen · 150 lines · 68 tokens per session scan A 1ad44e17cf83
kinde-authorization is a skill published in the GitHub repository ski043/kinde-agent-skills (2 stars, last pushed 18d ago), licensed MIT. It adds 68 tokens to every session and 2,274 once invoked, about $0.0003 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
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
nopua
A guidance skill for coding agents that promotes patient, thorough, self-directed work instead of fear or threats.
resemble-detect
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, and analyze media intelligence using direct Resemble AI API calls.
nopua-lite
NoPUA Lite — core wisdom in 1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models.
cinematic-scroll
Build or improve cinematic websites with scroll-driven storytelling, pinned reveals, parallax, kinetic type, and optional 3D. Deliver standalone HTML or integrate into an existing app, with mobile and reduced-motion fallbacks and browser evidence. Also supports scroll audits and motion storyboards. Use for cinematic…
ios-agent-skill
Expert iOS/Swift developer behavior for AI coding agents. Use when writing, reviewing, or refactoring Swift, SwiftUI, UIKit, or SwiftData code; when designing iOS app architecture (MVVM, Clean Architecture, coordinators, routing); when building UI that must meet Apple's Human Interface Guidelines, contrast, dark-mode…