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 instructions/moizibnyousaf/marketing-cli/claude-mdgit clone --depth 1 https://github.com/MoizIbnYousaf/marketing-cliWrote 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/instructions/moizibnyousaf/marketing-cli/claude-md)<a href="https://agentmods.dev/instructions/moizibnyousaf/marketing-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/moizibnyousaf/marketing-cli/claude-md.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 5.1 | $0.04029 | $0.04029 |
| Opus 5 | $0.02014 | $0.02014 |
| Sonnet 5 | $0.00806 | $0.00806 |
| Haiku 4.5 | $0.00403 | $0.00403 |
Grade B, and why
marketing-cli CLAUDE.md scanned grade B with 1 finding 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 6d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
**MCP + Exa skills:** Exa MCP for deep web research (wired via `.mcp.json`) plus first-class skills ported from [exa-labs/agent-skills](https://github.com/exa-labs/agent-skills): `exa-search`, `exa-contents`, `company-re How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mktg: Agent-Native Marketing Playbook CLI
[!IMPORTANT] For runtime CLI usage (commands, flags, output formats), read
CONTEXT.mdfirst. For/cmoruntime indexes, readskills/cmo/rules/cli-runtime-index.md,skills/cmo/rules/publish-index.md, andskills/cmo/rules/studio-api-index.md. For/axi(AXI catalog router), readskills/axi/SKILL.mdandskills/axi/rules/. For agent/skill contributor guidance, readAGENTS.md. This file is the project's development contract: architecture, standards, and rules.
What This Is
A TypeScript/Bun agent-native marketing playbook CLI. 76 marketing skills (74 playbook + /cmo + /axi), 6 agents (4 research + 2 review), 24 commands, 2 upstream catalogs (postiz, openseo). The Studio dashboard (Next.js + Bun API) ships inside the same tarball and is launched via mktg studio.
| Component | Count | Purpose |
|---|---|---|
mktg CLI |
24 commands | Infrastructure: setup, health, skill management, catalog registry, verification, and orchestration |
/cmo skill |
1 orchestrator | Routes every marketing request to the right skill |
/axi skill |
1 orchestrator | Routes agent-tool work to AXI-catalog CLIs (gh-axi, chrome-devtools-axi, …) |
brand/ directory |
10 memory files (+ SCHEMA.md) | Persistent marketing memory, compounds across sessions |
| Marketing skills | 76 total (74 playbook + /cmo + /axi) |
The playbook, installed to ~/.claude/skills/ |
| Marketing agents | 6 | Parallel sub-agents for research + review, installed to ~/.claude/agents/ |
| Upstream catalogs | 2 | External OSS projects mktg builds on (postiz = 30+ social providers via REST API, AGPL-firewalled; openseo = SEO data plane via research_adapters + MCP) |
| Studio dashboard | 1 | Next.js + Bun API workspace member at studio/, bundled in the tarball, launched via mktg studio |
Repo Layout
This is a bun-workspaces monorepo with one publishable package: marketing-cli. The studio/ subfolder is a workspace member; its source ships inside the marketing-cli tarball, so npm i -g marketing-cli installs the CLI and the dashboard together. The workspace exists because Studio is a Next.js app with its own build pipeline.
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.
- 6d ago First seen · 246 lines · 4,029 tokens per session scan B ed7b2576366e
marketing-cli CLAUDE.md is an instructions file published in the GitHub repository MoizIbnYousaf/marketing-cli (31 stars, last pushed 19d ago), licensed MIT. It adds 4,029 tokens to every session, about $0.0201 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
marketing-os AGENTS.md
Instructions for Yuzzyuk/marketing-os, covering marketing os — agent entry point, routing and standards that hold in any host.
tiktok-skills AGENTS.md
AGENTS.md instructions for sergebulaev/tiktok-skills, covering project conventions - tiktok-skills, versioning, commits, skill bundle invariants and voice rules + reference layout.
adaptico-os CLAUDE.md
Instructions for adaptico/adaptico-os, a project described as: The go-to-market operating system for early-stage software products. AI marketing skills for Claude Code - scored audits, stage-aware advice, per-project memory. For marketers and founders.
linkedin-skills CLAUDE.md
Claude Code instructions for sergebulaev/linkedin-skills, covering project conventions — linkedin-skills, versioning, commits, skill bundle invariants and voice rules + reference layout.
taketomarket GEMINI.md
Instructions for ranjanrishikesh/taketomarket, covering taketomarket for gemini cli, target audience, installation, invocation and quick start.