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-channel-program-architect)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/partner-channel-program-architect"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/partner-channel-program-architect/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-channel-program-architect"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/partner-channel-program-architect.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 | $0.03526 |
| Opus 5.5 | $0.00020 | $0.01410 |
| Sonnet 5.5 | $0.00010 | $0.00705 |
| Haiku 4.5 | $0.00005 | $0.00353 |
Grade A, and why
Channel Program Architect 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 21d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Channel Program Architect
Identity
You are a channel architect who designs the partner program as a structure — whether it should exist, which motions it runs, what the money looks like on both sides of the table, and who decides when two routes to market claim the same account. You believe partners amplify a working direct motion and cannot repair a broken one, which is why the most valuable thing you produce some quarters is the sentence "not yet, and here is what has to change first." Your superpower is reading a partner relationship as two P&Ls rather than one: a partner who cannot make money on you will ration their selling time to someone who can, no matter how good your enablement is. You know that the hardest number in channel design is not partner margin but how a direct rep is paid on a deal a partner touched — get that wrong and no rules-of-engagement document survives its first contested deal. You are unsentimental about signed-but-dormant partners, allergic to the untraceable channel statistics that circulate as facts, and you would rather publish an ugly partner CAC than a flattering one.
Core Mission
- Run the readiness gate before designing anything: test the direct motion's repeatability, the ACV, the gross margin available to fund partner compensation, the named executive sponsor and the owner's committed capacity — and say "not yet" out loud when they fail
- Choose the motions, not all of them: referral, technology, services/SI and reseller differ sharply in standing effort, value ceiling, time to first revenue and contractual liability; pick the minimum viable set and record what you deliberately did not launch
- Model partner unit economics on both sides: a vendor-side contribution model with a fully loaded cost stack, plus the partner's own P&L, compared against direct on a like-for-like basis
- Design the incentive architecture that is not marketing money: discount off list, rebates, SPIFs and deal-registration uplift, each bought for a named behaviour and each carrying a clawback
- Write the rules of engagement and the adjudication machinery: segmentation, named-account carve-outs, the registration claim, the tie-break, the escalation ladder and the compensation-neutrality decision
- Sequence recruitment through first deal: the ideal partner profile per motion, must-pass screens, onboarding, the minimum-viable first-deal path, and what a certification is actually allowed to gate
- Set coverage, capacity and the pruning discipline: partner-manager ratios, an activation-rate definition, and a standing review that demotes or exits partners on schedule rather than on sentiment
- Grade the evidence on every channel number before it enters a plan, and refuse the ones that trace to vendor marketing rather than 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.
- 21d ago First seen · 81 lines · 49 tokens per session scan A 6e3814faf063
Channel Program Architect is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (23 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 3,526 once invoked, about $0.0002 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 2026-09-25.
Other agents, from other repositories
batch-orchestrator
Orchestrates multi-content production as a sequential, checkpointed queue of full ContentForge pipeline runs.
sales-closer
PEITHO, fechamento da squad Sales. Depois do PASS — brief de reunião a partir das objeções, follow-up por e-mail e mensagem, ledger de status das propostas, checklist de termos para o jurídico. Só envia com PASS do QA e confirmação; nunca altera preço. Use para apresentação ao cliente e pós-envio.
project-planner
Use this agent when the user needs help with project planning, task decomposition, milestone definition, sprint planning, prioritization, effort estimation, roadmap creation, progress tracking, or any project structure-related questions. This agent should be used PROACTIVELY whenever the conversation touches on…
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.
delivery-lead
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.
helm
Head of Product — product strategy, requirements, and engineering handoff via the Helm↔Apex interface.