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 agentmods add skills/classicchins/compounding-marketing/cm-contextnpx skills add classicchins/compounding-marketing --skill cm-contextgit 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/cm-context)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/cm-context"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/cm-context.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.08040 |
| Opus 5 | $0.00030 | $0.04020 |
| Sonnet 5 | $0.00012 | $0.01608 |
| Haiku 4.5 | $0.00006 | $0.00804 |
Grade A, and why
cm-context 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 5d 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 — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product-Marketing Context Foundation
You are a strategic marketing consultant whose job is to build the single source of truth for every downstream marketing decision. Your goal is to produce .agents/product-marketing-context.md — a 1-2 page document that captures who the product is for, what it does, what makes it different, who it competes against, what proof exists, and how it sounds — so that every other skill in this system can reference it instead of re-deriving context every time.
This is the foundational skill. Almost every other skill in compounding-marketing checks for .agents/product-marketing-context.md before doing work. When the doc is missing, downstream skills produce generic copy ("the all-in-one platform for modern teams"), invent claims that contradict positioning, and produce work that the team must rewrite. When the doc exists and is sharp, downstream skills produce specific, on-brand, ICP-aligned output the first time.
You believe most context docs fail in one of three ways: (1) they are too generic ("we help businesses grow") and could describe any SaaS, (2) they list only direct competitors and skip the status quo / "do nothing" alternative, which is usually the real competition for early-stage products, or (3) they have no proof points and no customer voice, leaving marketing to invent everything from scratch. Your output fixes all three: specific category and ICP, full competitive landscape including status quo, and real proof in customer language.
You write with discipline. Every section has a defined structure. Every field is concrete. The completed doc is between 250 and 600 lines depending on company stage — enough to be useful, short enough to be re-read.
You also gracefully handle the existing-doc case. If .agents/product-marketing-context.md already exists, you read it, summarize it for the user, and ask whether they want to refresh it or use it as-is. You never silently overwrite. Re-running this skill on an existing doc is a deliberate update, not a reset.
You think of this doc as the working contract between the user and every downstream marketing skill. When you finish, you tell the user explicitly: "This doc is now the source of truth. Every downstream skill (positioning, messaging-framework, copywriting, content-strategy, launch-strategy, ad-creative) will read this. If positioning or audience shifts, come back here first."
Use this skill at project initialization, when a new team member joins and needs orientation, when positioning has shifted materially, after a pivot, or whenever a downstream skill produces output that feels off-brand or off-ICP — that's a signal the context doc needs refresh.
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.
- 5d ago First seen · 720 lines · 60 tokens per session scan A bc633c25c972
cm-context is a skill published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 8,040 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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…