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 shalintripathi/saas-marketing-agents --skill catalyst-orchestratorgit clone --depth 1 https://github.com/shalintripathi/saas-marketing-agentsWrote 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/shalintripathi/saas-marketing-agents/catalyst-orchestrator)<a href="https://agentmods.dev/skills/shalintripathi/saas-marketing-agents/catalyst-orchestrator"><img src="https://agentmods.dev/badge/skills/shalintripathi/saas-marketing-agents/catalyst-orchestrator/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/shalintripathi/saas-marketing-agents/catalyst-orchestrator"><img src="https://agentmods.dev/badge/skills/shalintripathi/saas-marketing-agents/catalyst-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00146 | $0.06930 |
| Opus 5.5 | $0.00058 | $0.02772 |
| Sonnet 5.5 | $0.00029 | $0.01386 |
| Haiku 4.5 | $0.00015 | $0.00693 |
Grade A, and why
catalyst-orchestrator 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 today.
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 — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CATALYST Orchestrator: Master Marketing Framework
Step 0 (always first): Load brand context
Before routing any work or producing any deliverable, look for a brand-context.md file in the user's project root (also check ./.claude/brand-context.md and ./docs/brand-context.md). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.
- If it exists: read it in full and treat it as binding for this run. Pass its contents to every specialist agent you route work to, along with the task brief. Its "Rules for agents reading this file" section overrides an agent's own defaults.
- If it does not exist: say so, point the user at the template (
templates/brand-context.md), and offer to generate a filled draft by interviewing them or by reading their website and existing content. Then proceed with explicitly-labelled assumptions — never silently invented ones.
Non-negotiable regardless of which path applies: do not invent customer names, metrics, funding, integrations, certifications, or outcomes. Only proof recorded in brand-context.md (or supplied directly in the request) may be used as fact. Where a claim would help but no evidence exists, emit a [NEEDS INPUT: …] marker in the deliverable rather than a plausible-sounding guess.
Brand context is what turns generic B2B SaaS output into output that sounds like the user's company. Skipping this step is the single most common cause of low-quality results.
What This Is
CATALYST (Coordinated Agents for Targeted, Analytics-Led, Year-round SaaS Transformation) is the master orchestration framework for enterprise-scale B2B SaaS marketing. It coordinates 91 specialized agents across 17 disciplines executing campaigns from strategy through optimization. CATALYST is designed for organizations that need simultaneous execution across multiple disciplines—not sequential waterfall, but parallel execution with intelligent coordination, quality gates, and escalation procedures.
What ships with it
7 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.
- today Changed 131d4929e3f9
- 21d ago Changed 57a1e33c43c6
- 22d ago Changed db2da2dca1b3
- 23d ago Changed a8f8c7d71bcc
- 24d ago Changed 8f461600bd17
- 26d ago Changed 763350df03ab
- 28d ago Changed c08efbcbbfa1
- 1mo ago Changed d7fc003cd3bd
- 1mo ago Changed 7e59345e0e20
- 1mo ago First seen · 546 lines · 146 tokens per session scan A 8a62f33e792f
catalyst-orchestrator is a skill published in the GitHub repository shalintripathi/saas-marketing-agents (30 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 6,930 once invoked, about $0.0006 per session on Opus 5.5. 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
batch-process
Batch-produce many content pieces as one resumable queue, highest priority first. "write these 15 posts".
cf-aeo-check
Re-check a published piece's AEO: cited in AI Overviews and AI answers, tracked over time. "did AI cite our article".
image-seo-audit
Audit image SEO on a page: alt text, weight, formats, srcset, lazy loading, CLS. "audit our image SEO".
client-proposal
Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP".
content-brief
Write an executable content brief: keyword map, outline, intent, SEO checklist. "write a brief for this topic".
email-sequence
Design an ESP-ready email sequence: subjects, copy, timing, branching, deliverability. "build a welcome sequence".