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 deeleeramone/PyWry --skill authenticationgit clone --depth 1 https://github.com/deeleeramone/PyWryWrote 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/deeleeramone/pywry/authentication)<a href="https://agentmods.dev/skills/deeleeramone/pywry/authentication"><img src="https://agentmods.dev/badge/skills/deeleeramone/pywry/authentication/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/deeleeramone/pywry/authentication"><img src="https://agentmods.dev/badge/skills/deeleeramone/pywry/authentication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 51 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00000 | $0.00927 |
| Opus 5.5 | $0.00000 | $0.00371 |
| Sonnet 5.5 | $0.00000 | $0.00185 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
authentication 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication & OAuth2
Add OAuth2 authentication to PyWry apps — Google, GitHub, Microsoft, or any OIDC provider.
Two Modes
Native Mode (Desktop)
Opens a dedicated auth window → user logs in at provider → callback captured on ephemeral localhost server → tokens returned.
from pywry import PyWry
app = PyWry()
result = app.login() # Blocks until auth completes
if result.success:
app.show("<h1>Welcome!</h1>")
app.block()
Deploy Mode (Production)
Auth routes mounted automatically when auth_enabled=True and oauth2 settings are configured.
PYWRY_DEPLOY__AUTH_ENABLED=true
PYWRY_OAUTH2__PROVIDER=google
PYWRY_OAUTH2__CLIENT_ID=your-id
PYWRY_OAUTH2__CLIENT_SECRET=your-secret
Routes: GET /auth/login, GET /auth/callback, POST /auth/refresh, POST /auth/logout, GET /auth/status, GET /auth/userinfo
Configuration
Environment Variables
# Provider: google, github, microsoft, oidc, custom
PYWRY_OAUTH2__PROVIDER=google
# Credentials
PYWRY_OAUTH2__CLIENT_ID=your-client-id
PYWRY_OAUTH2__CLIENT_SECRET=your-client-secret
# Scopes (space-separated)
PYWRY_OAUTH2__SCOPES=openid email profile
# PKCE (recommended for public clients)
PYWRY_OAUTH2__USE_PKCE=true
# Token storage: memory (default), keyring (native), redis (deploy)
PYWRY_OAUTH2__TOKEN_STORE_BACKEND=memory
# Custom provider endpoints
PYWRY_OAUTH2__AUTHORIZE_URL=https://provider.com/authorize
PYWRY_OAUTH2__TOKEN_URL=https://provider.com/token
# OIDC auto-discovery
PYWRY_OAUTH2__ISSUER_URL=https://accounts.google.com
TOML Configuration
[tool.pywry.oauth2]
provider = "github"
client_id = "your-id"
scopes = "read:user user:email"
use_pkce = true
token_store_backend = "memory"
Provider Setup
from pywry.auth import GoogleProvider
provider = GoogleProvider(client_id="...", client_secret="...")
result = app.login(provider=provider)
GitHub
from pywry.auth import GitHubProvider
provider = GitHubProvider(client_id="...", client_secret="...")
result = app.login(provider=provider)
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.
- 1mo ago First seen · 140 lines · 0 tokens per session scan A 9a1e6484c0c2
authentication is a skill published in the GitHub repository deeleeramone/PyWry (98 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 927 tokens. 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
build-fullstack-backend
ONLY for writing backend or fullstack code BY HAND. NOT needed on the normal path — createartifact(fullstack-stateless-app or fullstack-stateful-app) followed by generateartifact writes the backend, verifies it by importing it and launches it. Recall this when editing an existing fullstack artifact, or when…
node-red
Use when building IoT data flows and API integration with Node-RED low-code programming — inject/debug/function/change/switch nodes, the msg.payload message model, MQTT in/out broker configuration and pub/sub, HTTP in/out REST endpoints, context storage, subflows, node-red-dashboard panels, and settings.js…
saleor-development
Build and extend Saleor's GraphQL-based headless commerce platform with custom apps, webhook handlers, and dashboard UI customizations.
laravel-nova
Build custom administration panels using Laravel Nova with advanced fields, lenses, actions, and cards.
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…