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/dcode-co/logi-plugins/logi-rp-integratenpx skills add dcode-co/logi-plugins --skill logi-rp-integrategit clone --depth 1 https://github.com/dcode-co/logi-pluginsWhat 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 | $0.00146 | $0.04806 |
| Opus 5 | $0.00073 | $0.02403 |
| Sonnet 5 | $0.00029 | $0.00961 |
| Haiku 4.5 | $0.00015 | $0.00481 |
Grade A, and why
logi-rp-integrate scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl https://docs.1pass.dev/llms/integrations/<stack>.md` (`rails`, `nextjs`, `flutter`, `swift`, `android`, `kotlin`, `react-native`, `spa-serverless`, `express`). How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
logi RP Integration
This skill helps an AI assistant integrate logi (the consumer-facing 1pass identity service) into a Relying Party (RP) project. logi is a hosted OIDC-style IdP running live at https://api.1pass.dev — you do not need to self-host anything. You register your app, drop in standard OAuth wiring, and verify.
Mental model. logi behaves like an OpenID Connect provider for the standard web/server flow (Authorization Code + PKCE, OIDC discovery), but the mobile login experience is a Kakao/Naver-style "first-try" app-to-app handoff, not a plain ASWebAuthenticationSession. On native platforms, always use the published logi SDK or the documented first-try pattern — never a bare web-auth session (see Anti-pattern).
Authoritative docs (always prefer these over guessing — fetch the latest before non-trivial work):
- Full doc bundle for LLMs:
https://docs.1pass.dev/llms-full.txt - Topic index:
https://docs.1pass.dev/llms.txt - Per-topic markdown:
https://docs.1pass.dev/llms/<path>.md(e.g.llms/integrations/rails.md) - Developer console (register apps, manage scopes, secrets):
https://start.1pass.dev/developer/applications - Interactive flow demos:
https://demo.1pass.dev/ - Self-service login diagnostics for end users:
https://api.1pass.dev/diagnose
Conventions used throughout
| Item | Convention |
|---|---|
| IdP base URL | https://api.1pass.dev (set as LOGI_API_URL, no change needed) |
| Env var prefix | LOGI_* |
| Start route (web) | /auth/logi/start |
| Callback route (web) | /auth/logi/callback |
| Scopes | openid profile:basic email (standard SSO) |
| Mobile app id (first-try target) | dev.onepass.app (Android package) / applinks: + custom scheme (iOS) |
| Diagnostics | https://api.1pass.dev/diagnose |
Replace placeholders (logi_xxx, https://app.example.com, <your-app-host>) with the developer's real values.
Phase 0 — Pre-flight
Confirm with the developer:
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 · 387 lines · 146 tokens per session scan A 4b19afa6b609
logi-rp-integrate is a skill published in the GitHub repository dcode-co/logi-plugins (0 stars, last pushed 26d ago), licensed MIT. It adds 146 tokens to every session and 4,806 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…