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/agentry-ai/agentry/authnpx skills add agentry-ai/agentry --skill authgit clone --depth 1 https://github.com/agentry-ai/agentryWhat 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 | $0.00000 | $0.02372 |
| Opus 5 | $0.00000 | $0.01186 |
| Sonnet 5 | $0.00000 | $0.00474 |
| Haiku 4.5 | $0.00000 | $0.00237 |
Grade A, and why
auth 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Auth (sandbox-side, sidecar-served)
Use when the user says something like "add login", "users need to sign in", "I want auth", "gate this behind a user account". The auth surface (login / signup / OAuth / sessions) is NOT something you build. Read this whole page before touching auth code.
How auth works on agentry
When the operator runs agentry auth enable on their CLI, every
sandbox in that profile gets:
- A database binding (postgres, mysql, or mongodb). Reachable via
DATABASE_URL,POSTGRES_URL,MYSQL_URL, orMONGODB_URI. - The
authproxysidecar baked into the runtime image. Whenproject_startspawns your app, authproxy sits in front of it:
external --(:3000)--> authproxy --(127.0.0.1:3001)--> your app
Port discipline corollary (CONTRACT.md rule 1): because the
sidecar owns the public port, your start_command must NOT pass
--port / -p — your app reads the PORT env var (it will be
3001 when auth is on). A hard-coded port collides with the sidecar
and dies with address already in use. The scaffolded
start_command already does this; don't undo it.
If the auth surface itself misbehaves (403s on /auth/login, signup
loops, session not sticking): that is PLATFORM territory (CONTRACT
rule 5). Capture project_logs, report it to the user, and STOP. Do
not write warmup routes, do not edit ports, do not set competing
cookies from app code.
-
The sidecar serves the entire auth surface itself:
GET /auth/login— login formPOST /auth/login— credentials -> session cookieGET /auth/signup— signup formPOST /auth/signup— new user -> session cookiePOST /auth/logout— clear sessionGET /auth/me— JSON of the current user (or 401)GET /auth/oauth/<provider>/start— OAuth flow startGET /auth/oauth/<provider>/callback— OAuth callback
Configured providers (when the operator wired them):
google,github,microsoft,apple,generic-oidc.
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 · 267 lines · 0 tokens per session scan A 9537036bc889
auth is a skill published in the GitHub repository agentry-ai/agentry (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,372 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 2026-08-31.
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.