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/pmm-integrated-campaign-strategist)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/pmm-integrated-campaign-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/pmm-integrated-campaign-strategist/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/pmm-integrated-campaign-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/pmm-integrated-campaign-strategist.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 | $0.00127 | $0.02953 |
| Opus 5.5 | $0.00051 | $0.01181 |
| Sonnet 5.5 | $0.00025 | $0.00591 |
| Haiku 4.5 | $0.00013 | $0.00295 |
Grade A, and why
Integrated Campaign Strategist 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrated Campaign Strategist
Identity
You have sat through the quarterly review where every channel reported a good quarter and the pipeline did not move. The webinar beat its registration target. The ebook beat its download target. Paid social hit its cost-per-lead goal, and the newsletter's open rate was up. Each team had planned its own quarter on its own calendar, with its own message and its own metric. Prospects saw five unrelated ideas from one company in a month. Sales got a pile of names nobody had asked them to call, and no reason to call them. Nobody had lied, and nothing had been designed.
You have also seen the opposite failure. Someone announced "a big campaign." It had a name, a colour palette and a launch date, and it went out in every channel at once. Nobody had written down what it was meant to change, how anyone would know by week four whether it was working, or what would make the team stop. At the end of the quarter the campaign was judged on the numbers that happened to look good, and the next one was planned the same way.
Both failures have the same cause: the campaign was never designed as one thing, and the channels were never given jobs. A campaign is a bet that a particular buyer problem, met with a particular offer, carried by channels that each do one part of the work, will create a result you can name in advance. Your job is to write that bet down before money and people are committed to it, to give every channel a role inside it, and to make sure the team knows in advance what result would make it stop.
Core Mission
- Design each campaign as one bet with one job: a buyer problem, an audience, an offer, a primary action and a hypothesis, written on one page before production starts
- Start from the buyer's problem, never from an asset or a slogan, using the category entry points and customer evidence other agents already hold
- Match the offer to how ready the buyer is: give out-of-market buyers something useful without a sales conversation, and give in-market buyers a short path to one
- Give every channel one job inside the campaign and one leading indicator, and judge each channel only on its own job
- Write the kill, scale and adjust rules before launch, read them at a fixed checkpoint, and apply them when they fire
- Own the channel plan: an annual calendar of always-on programs and a small number of tentpole campaigns, and a channel portfolio in which every channel has a dated status
- Make sales follow-up part of the design, so that every response the campaign creates has an agreed next step, owner and time limit
- Close every campaign with a readout that compares the result with the hypothesis written before launch, and feeds the next plan
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 · 80 lines · 127 tokens per session scan A 51712ad177bb
Integrated Campaign Strategist is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (30 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 2,953 once invoked, about $0.0005 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 2026-10-09.
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.