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 catalystbyzoho/agent-skills --skill catalyst-by-zohogit clone --depth 1 https://github.com/catalystbyzoho/agent-skillsWrote 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/agent-skills/catalyst-by-zoho)<a href="https://agentmods.dev/skills/catalystbyzoho/agent-skills/catalyst-by-zoho"><img src="https://agentmods.dev/badge/skills/catalystbyzoho/agent-skills/catalyst-by-zoho/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/catalystbyzoho/agent-skills/catalyst-by-zoho"><img src="https://agentmods.dev/badge/skills/catalystbyzoho/agent-skills/catalyst-by-zoho.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
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 →
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 45 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 75 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 176 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00053 | $0.03973 |
| Opus 5 | $0.00026 | $0.01987 |
| Sonnet 5 | $0.00011 | $0.00795 |
| Haiku 4.5 | $0.00005 | $0.00397 |
Grade A, and why
catalyst-by-zoho 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 11d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catalyst by Zoho — Skill Index
This is the routing layer. Load the most specific matching skill — do not answer from this file alone.
Philosophy
- Prefer MCP over asking. If
CatalystbyZoho_*tools are available, use them. Never ask the user to copy IDs from the console. - Default to Development. Always target the Development environment unless the user explicitly says "production" or "deploy to prod".
- "Build an app" means Slate + Function by default. When a user says "build an app", "create an app", or "make a simple app" without specifying backend-only, the default output is a Slate frontend + Advanced I/O function backend. Do NOT build only a function and call it an app. If the user's intent is clearly backend-only (e.g. "build an API", "write a function"), skip Slate.
- Prefer Functions over AppSail for simple HTTP. Functions are cheaper (per-invocation billing), simpler to deploy, and require no infrastructure management. Reach for AppSail only when the use case genuinely requires a persistent process, or a custom runtime.
- Show cost before building. For any new infrastructure (functions, AppSail, Stratus buckets), load
catalyst-pricingand give a brief estimate before writing code. Most small projects stay within free tier — say so when true. - Recommend the current service, not the deprecated one. File Store → Stratus. Event Listeners → Signals. Cron → Job Scheduling. Never mention the deprecated name in generated code or config.
- Warn before the region bites. Circuits and Integration Functions do not work in most data centers. Check the user's DC before suggesting them.
How It Works
- Pre-flight — Check that
.catalystrcandcatalyst.jsonexist. If missing, use MCP to get org/project IDs and runcatalyst init --org <orgId> -p <projectId> -ni. Never use interactivecatalyst init. - MCP check — Look for
CatalystbyZoho_*tools. If available, use MCP to fetch org/project IDs instead of asking the user. - Route — Match the query to the most specific service in the routing table below.
- Load lazily — Read ONLY the single reference file needed for the current step. Do NOT preload multiple skills upfront. For "build an app" requests: (a) assume Slate frontend + AIO function unless the user says backend-only, (b) sketch the architecture briefly and confirm with the user before building, (c) then load one reference file per service as you write each part —
catalyst-slatefor the frontend,catalyst-functionsfor the backend. - Cost check — Only load
catalyst-pricingif the user specifically asks about cost, or if the plan includes AppSail, Stratus, or other paid-tier services. Skip for basic Functions + DataStore projects (likely free tier). - Answer — Provide code examples using the user's platform (Node.js, Python, Java, Web, or Mobile).
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.
- 11d ago First seen · 229 lines · 53 tokens per session scan A f1acd41e45c8
catalyst-by-zoho is a skill published in the GitHub repository catalystbyzoho/agent-skills (60 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 3,973 once invoked, about $0.0003 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
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
azure-eventhub-dotnet
Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
wikipedia
Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
cve
Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.