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 tushaarmehtaa/tushar-skills --skill auth-implementationgit clone --depth 1 https://github.com/tushaarmehtaa/tushar-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/tushaarmehtaa/tushar-skills/auth-implementation)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/auth-implementation"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/auth-implementation/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/tushaarmehtaa/tushar-skills/auth-implementation"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/auth-implementation.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 | $0.00039 | $0.01092 |
| Opus 5.5 | $0.00016 | $0.00437 |
| Sonnet 5.5 | $0.00008 | $0.00218 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
auth-implementation 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication implementation
Implement identity and authorization end to end. Prefer the existing provider. Do not introduce or replace an identity system without an explicit user decision.
Dated facts
Provider facts in the references carry a check date and source. Before acting on one, re-check the source if the date is more than 90 days old or the installed package version differs. For raw API shapes, use the provider's official agent skill if it is installed (clerk/skills, better-auth/skills, supabase/agent-skills), otherwise the provider's docs for the installed version. This skill keeps the judgment: access matrix, enforcement points, safe linking, idempotent sync and negative tests.
Workflow
- Detect framework/router version, auth package and installed version, database/ORM, session transport, user/account tables, tenant model, middleware or proxy, protected resources, and existing migrations.
- Distinguish authentication from authorization. Write an access matrix for public, signed-in, owner, team member, admin, and service/background paths that actually exist.
- Decide whether a local user mirror is necessary. If it is, model provider identities separately from application users when multiple login methods or providers are possible. Never link accounts from an unverified client-supplied email.
- Ask only when a material choice remains: provider selection, account-linking policy, deletion behavior, organization/tenant model, or whether existing users must be backfilled.
- Use the matching provider reference only after detecting the exact stack and installed version. When the project already has an auth library, that library is the default. Do not route it to another one.
- Clerk for resource-level protection, verified user synchronization and Clerk tokens for Supabase.
- Auth.js / NextAuth for existing Auth.js projects only. Detect v4 or v5 beta first.
- Better Auth for projects already on Better Auth, or a new project where the user chose a self-hosted library.
- Supabase Auth for the identity model and profile synchronization. The
supabaseskill owns Supabase grants, RLS, API keys and server session checks. - For Firebase, Auth0, custom JWT, or a provider/database combination not covered, preserve existing code and use that provider's documentation for the installed version instead of adapting an incompatible example.
- New project with no auth: provider choice is the user's call (step 4). Offer a hosted provider (Clerk, Supabase Auth) or a self-hosted library. For a self-hosted library, recommend Better Auth over Auth.js. Auth.js v5 never left beta, npm
lateststill installs v4, and Auth.js has been in security-patch mode under the Better Auth team since 22 Sep 2025 (checked 2026-11-04: https://better-auth.com/blog/authjs-joins-better-auth, https://registry.npmjs.org/-/package/next-auth/dist-tags).
- Enforce access next to every protected read/mutation. Middleware/proxy may provide broad routing, but it is not the sole authorization boundary.
- When data goes through the Supabase Data API, every exposed table needs explicit grants and RLS in the same migration as
create table. Default grants vary by project: new projects stopped auto-granting from 30 May 2026, and enforcement on existing projects was scheduled for 30 Oct 2026. Where grants are missing, the Data API returns42501(checked 2026-11-04: https://supabase.com/changelog/45329-breaking-change-tables-not-exposed-to-data-and-graphql-api-automatically, https://supabase.com/docs/guides/api/securing-your-api). Follow thesupabaseskill for grants, policies, keys and SSR sessions. If it is not installed, use https://supabase.com/docs/guides/api/securing-your-api. - Make sync idempotent and verifiable. Prefer signed provider webhooks for lifecycle sync, or fetch authoritative provider data on the server for just-in-time sync. Handle create, update, merge, deletion, replay, out-of-order delivery, and backfill.
What ships with it
4 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.
- 2d ago Changed · +6 lines a24b98f4c0b5
- 2mo ago First seen · 33 lines · 39 tokens per session scan A 2d37fb8bc56b
auth-implementation is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (12 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 1,092 once invoked, about $0.0002 per session on Opus 5.5. 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.
auth-implementation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| auth-implementationtushaarmehtaa/tushar-skills | Skill | 12 | 2d ago | MIT | A | 39 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | today | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | today | MIT | A | 46 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 3d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | today | MIT | A | 106 | Claude Code |
| telnyx-messaging-hosted-curlteam-telnyx/ai | Skill | 224 | today | MIT | A | 45 | Claude Code |