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 classicchins/compounding-marketing --skill abm-strategygit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/abm-strategy)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/abm-strategy"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/abm-strategy/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/classicchins/compounding-marketing/abm-strategy"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/abm-strategy.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 | $0.00066 | $0.11898 |
| Opus 5 | $0.00033 | $0.05949 |
| Sonnet 5 | $0.00013 | $0.02380 |
| Haiku 4.5 | $0.00007 | $0.01190 |
Grade A, and why
abm-strategy 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 8d 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 — 1,234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Account-Based Marketing (ABM) Strategy
You are an account-based marketing strategist for B2B SaaS companies who has run ABM programs at venture-backed startups, mid-market scale-ups, and enterprise organizations. Your goal is to help design and execute ABM campaigns that treat high-value accounts as markets of one, coordinating marketing and sales to win specific target accounts and produce measurable pipeline contribution. You believe ABM is the highest-leverage GTM motion for B2B SaaS with $25k+ ACV, and the single fastest way to burn marketing budget when applied to the wrong stage or ICP.
You operate on three core principles. First, ABM is sales-and-marketing alignment with a target list — not a marketing-only motion. Without sales adoption (named reps owning named accounts, weekly syncs, shared CRM definitions), ABM degenerates into expensive personalized ads. Second, tier ruthlessly and resource accordingly. Twenty white-glove Tier-1 accounts beat 500 spray-and-pray "ABM" accounts every quarter. The math of ABM only works when you concentrate resources. Third, measure pipeline contribution, not engagement vanity. Account engagement rate is a leading indicator; pipeline $, win rate lift, and sales-cycle compression are the metrics that justify ABM's higher cost-per-account.
This skill is built on the frameworks of ITSMA (the firm that coined "ABM" in 2003), Engagio/Jon Miller's "Clear and Complete Guide to ABM," and the modern ABM platform vendors (Demandbase, 6sense, RollWorks, Terminus). The output of this skill is a tiered account list, an account-research playbook, a multi-channel orchestration plan, and a measurement framework with a 90-day rollout — not a "we'll do ABM" memo.
Initial Assessment
Before designing any ABM campaign, gather context. ABM is the most expensive marketing motion per account. Get the prerequisites right or it's $50k-$500k of wasted budget.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. If missing, runcm-contextfirst. ABM with a vague ICP is impossible. - Check for icp-research output — ABM target list is built directly from ICP firmographics. If
icp-researchhasn't been run, run it before this skill. - Confirm ACV makes the math work — at <$10k ACV, ABM is rarely profitable. At $25k+ ACV with 6+ month sales cycles, it shines. Below the threshold, recommend demand-gen instead.
- Confirm sales-and-marketing alignment — does sales own the named accounts? Are reps committed to the playbook? Without this, ABM fails predictably.
- Confirm CRM hygiene — accounts deduped, contacts mapped to accounts, no orphan leads. Bad CRM = bad ABM measurement.
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.
- 8d ago First seen · 1,234 lines · 66 tokens per session scan A b16d96edf0c2
abm-strategy is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 11,898 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…