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 Salesably/salesably-marketplace --skill orchestratorgit clone --depth 1 https://github.com/Salesably/salesably-marketplaceWrote 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/salesably/salesably-marketplace/orchestrator)<a href="https://agentmods.dev/skills/salesably/salesably-marketplace/orchestrator"><img src="https://agentmods.dev/badge/skills/salesably/salesably-marketplace/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/salesably/salesably-marketplace/orchestrator"><img src="https://agentmods.dev/badge/skills/salesably/salesably-marketplace/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 | $0.00049 | $0.02187 |
| Opus 5 | $0.00024 | $0.01094 |
| Sonnet 5 | $0.00010 | $0.00437 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
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 12d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator
This skill acts as a routing system for marketing projects - diagnosing needs, recommending the right skills, and sequencing them for comprehensive campaign execution.
Objective
Help users navigate the marketing skills suite by identifying the right skill(s) for their needs and sequencing them effectively for multi-step projects.
The 10 Marketing Skills Available
Foundation Layer
| Skill | Purpose | Use When |
|---|---|---|
brand-voice |
Define consistent communication | Starting from scratch, content sounds generic, need consistency |
positioning-angles |
Find market differentiation | New product, competitive market, unclear positioning |
Strategy Layer
| Skill | Purpose | Use When |
|---|---|---|
keyword-research |
Identify content opportunities | Building content strategy, filling calendar, finding topics |
lead-magnet |
Create opt-in offers | Growing email list, launching product, need leads |
Execution Layer
| Skill | Purpose | Use When |
|---|---|---|
direct-response-copy |
Write conversion-focused copy | Sales pages, landing pages, any conversion goal |
seo-content |
Create search-optimized articles | Blog posts, pillar content, organic traffic goals |
newsletter |
Build recurring engagement | Regular audience communication, email content |
email-sequences |
Automate customer journeys | Welcome flows, launches, conversions, onboarding |
Distribution Layer
| Skill | Purpose | Use When |
|---|---|---|
content-atomizer |
Repurpose across platforms | Maximizing content ROI, filling calendars, multi-platform |
Diagnostic Questions
To identify the right skill, ask:
1. What's the primary goal?
- Build awareness →
seo-content,content-atomizer,newsletter - Generate leads →
lead-magnet,direct-response-copy,email-sequences - Convert to sales →
direct-response-copy,email-sequences - Retain customers →
email-sequences,newsletter - Define brand →
brand-voice,positioning-angles - Plan content →
keyword-research
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.
- 12d ago First seen · 246 lines · 49 tokens per session scan A 2afe826ed0b7
orchestrator is a skill published in the GitHub repository Salesably/salesably-marketplace (49 stars, last pushed 8mo ago), licensed MIT. It adds 49 tokens to every session and 2,187 once invoked, about $0.0002 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
gtm-brain-builder
Orchestrate the creation or maintenance of a source-backed GTM brain for a company, including tool connection, section routing, Grill-me questions, session relay, section-agent sequencing, and recurring freshness workflows. Use when a user wants to build a GTM Brain or make one shareable/useful for sales, marketing…
design-system-agent
Create a source-backed design-system brief and walk an operator through using Claude.ai/design or Codex design workflows to generate, review, export, and import a brand kit/design system into the GTM Brain.
grill-me
Always-on decision-quality skill for stress-testing GTM brain claims, positioning, ICP, proof, tone, campaign learnings, source interpretation, and strategy branches by asking one pointed operator question at a time with a recommended hypothesis.
brand-voice-agent
Build brand guidance and separate speaker-tone profiles for a GTM brain, keeping person-specific tone distinct from sales-copy substance and buyer language.
customer-icp-agent
Build customer, proof, ICP, persona, and segment context from revenue, CRM, product usage, support, customer language, and accountable-owner review.
messaging-market-agent
Build buyer language, objections, value props, positioning, offers, competitors, alternatives, and market context from public story, customer/prospect evidence, campaigns, calls, CRM, and operator review.