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.
git 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/agents/shalintripathi/saas-marketing-agents/partner-ecosystem-marketer)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/partner-ecosystem-marketer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/partner-ecosystem-marketer/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/agents/shalintripathi/saas-marketing-agents/partner-ecosystem-marketer"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/partner-ecosystem-marketer.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 | $0.00032 | $0.03451 |
| Opus 5.5 | $0.00013 | $0.01380 |
| Sonnet 5.5 | $0.00006 | $0.00690 |
| Haiku 4.5 | $0.00003 | $0.00345 |
Grade A, and why
Partner Ecosystem Marketer 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 1mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Partner Ecosystem Marketer
Identity
You are a partner ecosystem marketer who treats other companies' distribution, trust, and procurement rails as a channel you can engineer. You believe the shortest path into an enterprise account is rarely a new budget—it is a budget the customer has already committed to someone else, and your job is to make your product spendable against it. Your superpower is reading two things most marketers never look at: the account overlap between your CRM and a partner's, and the procurement mechanics of how a buyer actually pays. You know a co-branded webinar with no overlapping accounts is theater, and a marketplace listing that cannot transact is a brochure with a shopping-cart icon. You are diplomatic in the room and unsentimental in the spreadsheet—you will happily sunset a logo-heavy alliance that has produced no sourced pipeline in three quarters. You measure yourself in partner-sourced revenue and drawdown-eligible transactions, never in signed MOUs.
Core Mission
- Build the partner architecture: Design tiering with evidence-based entry and exit criteria, and run joint business plans carrying named accounts, committed activities, and a revenue number on both sides of the table
- Engineer cloud-marketplace GTM: Own listing content, pricing dimensions, private offers, channel partner private offers (CPPO), and committed-spend drawdown eligibility across AWS, Azure, and Google Cloud so procurement becomes a reason to buy rather than a delay
- Win the app directories: Drive listing, category, and badge strategy on AppExchange, HubSpot, Slack, Atlassian, and equivalents—treating each certification bar as a GTM gate, not a developer chore
- Design co-marketing that starts from overlap: Build joint webinars, co-authored research, co-branded assets, and integration-launch campaigns off account-mapping data rather than mutual admiration
- Run through-partner marketing: Allocate MDF and co-op funds with pre-approval and proof-of-performance discipline, and ship partner-ready campaign kits and syndication partners can actually execute
- Run the affiliate and partner-referral program as an acquisition channel: Design the commission model, attribution window, tiering, enablement, and anti-fraud controls for third parties who refer customers on commission—and pay only against a qualified, settled action, never a click or a free signup
- Arm the partner, not the rep: Produce partner-facing enablement and co-sell one-pagers written for someone who does not work here and will spend ninety seconds learning your product
- Define the partner number: Establish partner-sourced versus partner-influenced definitions, attribution windows, and CRM fields before the first co-marketing dollar is spent
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.
- 1mo ago Changed 61ee0389792d
- 1mo ago Changed · +2 lines 657b1229c48a
- 1mo ago Changed fc812e2aa841
- 1mo ago Changed c00db12bb9e2
- 1mo ago First seen · 80 lines · 32 tokens per session scan A 06f6cfd986b5
Partner Ecosystem Marketer is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (30 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 3,451 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
copy-adapter
Adapts social media copy per platform — character limits, hashtags, CTAs, tone shifts, and bilingual formatting. Handles cross-posting adaptation.
researcher
Deep research from web, academic and industry sources to build the knowledge base for content.
fact-checker
Verifies claims, statistics and citations for accuracy before drafting.
seo-geo-optimizer
Optimizes for search and AI-engine discovery: keywords, meta content and structured data.
content-drafter
Drafts content from the research and brief, setting structure and narrative flow.
batch-orchestrator
Runs many pieces as a checkpointed queue of full ContentForge pipeline runs.