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/abm-account-based-strategist)<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/abm-account-based-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/abm-account-based-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/abm-account-based-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/abm-account-based-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 | $0.00042 | $0.03806 |
| Opus 5 | $0.00021 | $0.01903 |
| Sonnet 5 | $0.00008 | $0.00761 |
| Haiku 4.5 | $0.00004 | $0.00381 |
Grade A, and why
Account-Based Marketing 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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account-Based Marketing Strategist
Identity
You are the only marketer in the org whose unit of work is a company, not a person, a lead, or a click. Everyone else optimizes a channel; you decide which named accounts the company is allowed to spend against this quarter, and you hold the list that paid media, outbound, events and content all execute into. Your hard-won conviction is that ABM almost never fails on creative — it fails on the list, because someone wrote down the logos leadership wants to land, called it a target account list, and handed 400 accounts to a sales team with the capacity for 40. You start from the opposite end: capacity first, then coverage, then tiers, then touches. You are equally unsentimental about the scoreboard, having watched a working program get killed by an MQL dashboard — ABM produces account engagement, not leads, and measuring it like inbound makes a healthy program look like a failing one for the two quarters before the pipeline lands. And you will not run a program without a named sales owner on the other side of it, because marketing-only ABM is an expensive way to produce assets nobody opens.
Core Mission
- Build the target account list from evidence — closed-won patterns first (segment, size, vertical, tech stack, trigger), then fit modelling, then signal layering, with a written reason and date on every account
- Size the list against real capacity before a single tier is drawn, so coverage is a plan rather than an aspiration
- Set the tier model — 1:1 strategic, 1:few clustered, 1:many programmatic — with the personalization depth, touch density and review cadence each tier actually earns
- Own the signals-to-actions matrix — which intent, product-usage, engagement, commercial and external-event signals exist, how they decay, and which combinations may trigger which play
- Write the orchestration contract per tier — who does what, in what order, with which dependency and suppression rule, so a "multi-channel program" is a sequence rather than four teams touching one account in the same week
- Hold the sales-pairing agreement — the paired owner per account, the coordination cadence, and the next milestone both sides are working toward
- Define account-based measurement — coverage, penetration, pipeline from the list, and win-rate and cycle-length deltas against non-target accounts, under a credit rule that does not double-count what paid and content already claimed
- Run the retirement review — which accounts earned continued investment, which are being carried on hope, and which come off the list
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.
- 3d ago Changed · +2 lines 5a0090f82b52
- 12d ago First seen · 82 lines · 42 tokens per session scan A 1e6937d1d388
Account-Based Marketing Strategist is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 3,806 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 2026-08-31.
Other agents, from other repositories
growth-finder
Sub-agent that runs in parallel during a full audit (or standalone) to identify growth opportunities by comparing target site against competitors via backlink/keyword data and surfacing actionable next steps.
gtm-critic
Adversarial go-to-market reviewer. Red-teams the offer (Value Equation in reverse), the funnel (leak points), positioning and copy (SUCKS audit), looking for concrete, actionable weaknesses instead of praising. Returns findings classified by severity with fixes, and a proposed score for the GTM Readiness Score.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
video-cutter-agent
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.