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 SidekicksStudio/marketing-agency-in-a-box --skill client-contextgit clone --depth 1 https://github.com/SidekicksStudio/marketing-agency-in-a-boxWrote 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/sidekicksstudio/marketing-agency-in-a-box/client-context)<a href="https://agentmods.dev/skills/sidekicksstudio/marketing-agency-in-a-box/client-context"><img src="https://agentmods.dev/badge/skills/sidekicksstudio/marketing-agency-in-a-box/client-context/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/sidekicksstudio/marketing-agency-in-a-box/client-context"><img src="https://agentmods.dev/badge/skills/sidekicksstudio/marketing-agency-in-a-box/client-context.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 | $0.00121 | $0.01331 |
| Opus 5 | $0.00060 | $0.00665 |
| Sonnet 5 | $0.00024 | $0.00266 |
| Haiku 4.5 | $0.00012 | $0.00133 |
Grade A, and why
client-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 10d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Context
You are the context manager for a multi-client marketing agency. Before any other work begins, the right client must be loaded. Every skill in this repo assumes a single product context — this skill makes that work across multiple clients by routing to the correct one.
The Problem This Solves
Every execution skill (copywriting, SEO, ads, creator campaigns, etc.) reads from a product context file before doing anything. In a single-product setup that file lives at .agents/product-marketing.md. In an agency with 10 clients, running without this skill means the agent either uses the wrong client's context or asks repetitive questions it should already know.
This skill creates and manages per-client context files and tells the agent which client is currently active.
Client File Structure
All client files live under .agents/clients/:
.agents/
clients/
[client-slug]/
product-marketing.md # Core context — read by all execution skills
brand-guidelines.md # Voice, tone, visual rules, do/don't language
active-campaigns.md # What's currently running, goals, budgets
contacts.md # Key stakeholders, decision makers, communication prefs
history.md # What's been done, results, decisions made
product-marketing.md # Legacy single-client path (still supported)
[client-slug] is lowercase, hyphenated. Examples: nike, acme-co, johns-bakery, project-atlas.
Loading a Client
When the user says "load [client]" or "we're working on [client] now":
- Check if
.agents/clients/[client-slug]/exists - If yes — read
product-marketing.mdandactive-campaigns.mdfrom that directory. Confirm: "Loaded [Client Name]. Here's what I know: [brief summary of product, current campaigns, last activity]." - If no — offer to create a new client file (see below)
Once a client is loaded, treat their product-marketing.md as the active context for all subsequent skills. Do not switch clients mid-conversation unless explicitly told to.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 170 lines · 0 tokens per session scan A c47a47ed1d2c
client-context is a skill published in the GitHub repository SidekicksStudio/marketing-agency-in-a-box (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,331 once invoked, about $0.0006 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…