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/agora-oss-org/agora-plugins/sdknpx skills add agora-oss-org/agora-plugins --skill sdkgit clone --depth 1 https://github.com/agora-oss-org/agora-pluginsWrote 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/agora-oss-org/agora-plugins/sdk)<a href="https://agentmods.dev/skills/agora-oss-org/agora-plugins/sdk"><img src="https://agentmods.dev/badge/skills/agora-oss-org/agora-plugins/sdk.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.02134 |
| Opus 5 | $0.00049 | $0.01067 |
| Sonnet 5 | $0.00020 | $0.00427 |
| Haiku 4.5 | $0.00010 | $0.00213 |
Grade A, and why
sdk 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agora SDK
Agora is an open-source social-features framework (comments, reactions, feeds, follows, spaces, chat, notifications, auth) for React, React Native, and Expo. It is a fork of Replyke, rescoped to @agora-sdk/*.
Core principle: own the divergences, look up the rest
Agora is API-compatible with Replyke v7, so for the shared 80% (exact hook arguments, data-model fields) you look things up rather than memorize — see the lookup ladder below. This skill's hand-written value is the judgment layer: the mental model, the per-domain topology/gotchas, and the four fork divergences. Apply the divergence table to anything you derive from upstream Replyke docs — an agent that copies them verbatim produces code that won't compile or silently hits the wrong server.
Looking things up (works with or without the Replyke MCP)
Use the first source available — they degrade gracefully, and none of the lower tiers need a network or the MCP:
- Bundled API surface → references/api-surface.md. A self-contained index of every exported provider/hook/type grouped by domain. Always present; start here to find which symbol you need.
- The installed
.d.ts(the version-exact floor) → the consuming app has the packages innode_modules, so the real declarations are on disk:cat node_modules/@agora-sdk/core/dist/esm/index.d.ts, or drill in, e.g.cat node_modules/@agora-sdk/core/dist/esm/hooks/auth/useAuth.d.ts. This is the most accurate source — it's literally the version installed — and needs no network or MCP. Use it for exact signatures and field shapes. - Replyke docs MCP (if mounted) — richest prose + examples:
search_replyke_documentation(query)for concepts;query_docs_filesystem_replyke_documentationto read pages, e.g.cat /v7/hooks/comments/use-create-comment.mdx,ls /v7/hooks. docs.replyke.comvia WebFetch (if no MCP but online) — the same docs publicly. Start at the machine indexhttps://docs.replyke.com/llms.txtto discover exact page paths, then fetch any page's clean-markdown twin by appending.md, e.g.https://docs.replyke.com/v7/hooks/comments/use-create-comment.md. Paths are/v7/-prefixed (the same suffix used in the→pointers throughout these reference files) — unversioned paths 404.
What ships with it
6 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.
- 5d ago First seen · 86 lines · 99 tokens per session scan A 93798071320b
sdk is a skill published in the GitHub repository agora-oss-org/agora-plugins (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 99 tokens to every session and 2,134 once invoked, about $0.0005 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
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
slide-authoring
Technical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, layout, palette/visual direction, assets, speaker notes, stepped reveals, page transitions, and morph transitions. Consult this whenever you are about to write or modify any file under slides/ /, including from…
create-theme
Use this skill when the user wants to create, draft, author, or extract a slide theme in this open-slide repo. Triggers on phrases like "create a theme", "make a theme called X", "extract a theme from ", "build a theme from these images". Produces two paired files under themes/ — .md (palette, typography, layout…
apply-comments
Apply pending @slide-comment markers written by the open-slide inspector tool. Use when the user asks to "apply comments", "process slide comments", "apply the inspector comments", or references markers left inside slides/ /index.tsx.
current-slide
Resolve which slide, page, and (optionally) selected element the user is currently viewing in the open-slide dev server. Consult this whenever the user references "this page", "this slide", "this element", "the slide I'm on", "the current page", or any deictic reference to slide content without naming it. Re-read…
create-slide
Use this skill when the user wants to create, draft, author, or generate new slides / a presentation in this open-slide repo. Triggers on phrases like "make slides about X", "make a deck about X", "create a presentation", "draft slides for", "new slide", "a deck with speaker notes / a script", or when the user asks to…