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/catalystbyzoho/claude-plugin/catalyst-slatenpx skills add catalystbyzoho/claude-plugin --skill catalyst-slategit clone --depth 1 https://github.com/catalystbyzoho/claude-pluginWrote 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/catalystbyzoho/claude-plugin/catalyst-slate)<a href="https://agentmods.dev/skills/catalystbyzoho/claude-plugin/catalyst-slate"><img src="https://agentmods.dev/badge/skills/catalystbyzoho/claude-plugin/catalyst-slate.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 | $0.00120 | $0.01210 |
| Opus 5 | $0.00060 | $0.00605 |
| Sonnet 5 | $0.00024 | $0.00242 |
| Haiku 4.5 | $0.00012 | $0.00121 |
Grade A, and why
catalyst-slate 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚦 To run the app locally, use plain
catalyst serveFor any "start the server / run the app / start locally" request, prefer plain
catalyst serve(no--only) — it serves the whole project (Slate + Functions + AppSail) so the frontend can call your own backend. NEVER run the native dev server (npm run dev,vite,next dev,ng serve, …); it skips the Catalyst wrapper (/__catalyst/sdk/init.js, session cookie, ZAID, managed-service proxy), so auth,getCurrentUser, and session-backed calls silently fail though the UI renders — the #1 "auth broken locally" cause. Scope with--only/--except(e.g.--only slate) when a full serve errors out, or to isolate/speed up one component. Details:references/slate-basics.md→ CLI Commands; auth testing:../catalyst-authentication/.
How It Works
Before the MCP calls below, establish context once per session via the workspace readiness gate:
../catalyst-basics/references/preflight.md. It resolves and reconciles the org/project soCatalystbyZoho_List_All_Slate_Appsuses the correct project ID.
- Check if Slate is activated — Use MCP: call
CatalystbyZoho_List_All_Slate_Appswith the project ID.- If it returns apps or an empty list → Slate is activated. Proceed.
- If it returns an error or "not found" → Slate needs a one-time activation. Tell the user:
"Please open the Catalyst console, go to your project → Slate (left sidebar) → click Start Exploring. This is a one-time step that takes 5 seconds. Let me know when done and I'll continue." Wait for confirmation, then proceed.
- Never fall back to Web Client (legacy) because Slate isn't activated yet. Web Client is deprecated — Slate is always the right choice for frontend hosting. The one-time activation is not a reason to change the approach.
If Slate was not enabled during
catalyst init, runcatalyst slate:create --name <name> --framework <framework> -niimmediately after init. This command updatescatalyst.jsonnon-interactively — it is faster than manual setup and should be the default recommendation. - Check if Slate app exists — If no app exists yet, run
catalyst slate:create --name <name> --framework <framework> -nito scaffold one. If Slate was not selected duringcatalyst init, run this immediately after init. - Load
references/slate-basics.md— for framework setup,slate-config.tomlformat, and baseUrl configuration. - Cross-domain calls — If the query involves calling functions from a Slate app, apply the full URL +
generateAuthToken()+ CORS whitelist pattern.⚠️ Migrating from basic client hosting? Relative paths like
/server/fn/executethat worked in basic client silently break on Slate — Slate is served from*.onslate.comwhile functions are on*.catalystserverless.com. Every function call must become an absolute URL. Find and replace all relative/server/...paths with the fullhttps://<project>.catalystserverless.com/server/...URL and addgenerateAuthToken()headers. - Serve & test locally, THEN deploy (local-first). Run plain
catalyst serve(see the 🚦 rule above — never the native dev server), open the printed local URL, and click through the UI to verify the frontend renders and its function/API calls succeed (managed-service calls proxy to Development). Run any frontend test/build (npm test,npm run build). Iterate locally until it works. - Deploy to Development — only after the local pass:
catalyst deploy slate <name> -nideploys to the current environment. Preview URLs are available after the build completes. Verify on the deployed URL before promoting to Production. Full loop:../catalyst-basics/references/project-basics.md→ Environments.
What ships with it
1 file 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 · 39 lines · 120 tokens per session scan A 3bc2a27aa515
catalyst-slate is a skill published in the GitHub repository catalystbyzoho/claude-plugin (0 stars, last pushed 24d ago), licensed Apache-2.0. It adds 120 tokens to every session and 1,210 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…