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/fullstack-phoenix/saas_kit/oauthnpx skills add fullstack-phoenix/saas_kit --skill oauthgit clone --depth 1 https://github.com/fullstack-phoenix/saas_kitWhat 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 | $0.00044 | $0.01363 |
| Opus 5 | $0.00022 | $0.00681 |
| Sonnet 5 | $0.00009 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
oauth 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OAuth Login
Adds GitHub OAuth sign-in on top of the existing authentication feature. Built on
Ueberauth, it generates a UserIdentity schema that links OAuth accounts to your
users by email, an OauthCallbackController that handles the full request/callback
flow, and "Sign in with Github" buttons on the login and registration pages. New
OAuth users are auto-created and confirmed; existing users are matched and linked by
email.
When to use
- The app already has email/password auth and you want to add "Sign in with GitHub".
- You want OAuth users automatically linked to existing accounts by email, with no separate account silo.
- Don't reach for this if you have no users yet — install
authenticationfirst. Don't use it as your only auth: it extends the password flow, not replaces it.
Dependencies
- Requires:
authentication(theUserschema,Userscontext, and login/registration LiveViews must already exist). - Recommended: None.
Install
mix saaskit.feature.install oauth
No interactive decisions. The installer adds ueberauth and ueberauth_github to
mix.exs, injects Ueberauth config, mounts the /auth routes, generates the
user-identity context and controller, and adds the sign-in buttons.
What it generates
lib/my_app/user_identities.ex— context.find_or_create_user/1resolves the four identity/user scenarios (register, log in, link, re-link) and returns{:ok, user}or{:just_created, user}. Also CRUD:list_user_identities/1,create_user_identity/2.lib/my_app/user_identities/user_identity.ex— schema for theuser_identitiestable (provider,uid,belongs_to :user).lib/my_app_web/controllers/oauth_callback_controller.ex— handlesGET /auth/:providerandGET /auth/:provider/callback, logs the user in viaUserAuth.log_in_user/2.lib/my_app/ecto_helpers/stringable.ex— Ecto type for theprovider/uidfields.- Migration
priv/repo/migrations/*_create_user_identities.exs—user_identitiestable with a unique index on(uid, provider). - Injects
Users.confirm_user/1intolib/my_app/users.ex(used to auto-confirm verified OAuth sign-ins). - Adds the
/authscope tolib/my_app_web/router.exand "Sign in with Github" buttons to the login and registration LiveViews. - Tests + fixtures:
test/my_app/user_identities_test.exs,test/support/fixtures/user_identities_fixtures.ex.
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 · 139 lines · 44 tokens per session scan A 013bafa8ea51
oauth is a skill published in the GitHub repository fullstack-phoenix/saas_kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,363 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.