marketing-cli AGENTS.md

marketing-cli AGENTS.md is an instructions file for Codex, OpenCode from MoizIbnYousaf/marketing-cli. It costs 5,424 tokens per session, scanned B, original, MIT.

A repository instruction file for a marketing command-line tool with specialised AI agents, skills and commands. It describes how the agents are registered, used and installed.

In plain words
What is it for?
It helps maintain marketing research and review agents, the skill registry, drop-in skills and the commands that coordinate them.
Why use it?
It gives coding agents the contracts and security rules needed to change the marketing system without breaking how its parts work together.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/moizibnyousaf/marketing-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/MoizIbnYousaf/marketing-cli

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for marketing-cli AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/moizibnyousaf/marketing-cli/agents-md.svg)](https://agentmods.dev/instructions/moizibnyousaf/marketing-cli/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/moizibnyousaf/marketing-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/moizibnyousaf/marketing-cli/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,424 This file is loaded in full into every session.
When invoked 5,424 The same file — it is already loaded in full.
Security scan B 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05424 $0.05424
Opus 5 $0.02712 $0.02712
Sonnet 5 $0.01085 $0.01085
Haiku 4.5 $0.00542 $0.00542

Measured 4d ago against content hash e69cc99ed1b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

marketing-cli AGENTS.md scanned grade B with 3 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 4d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

2. **`mktg verify` / `mktg ship-check` suite reachability**: those commands resolve suites as `<mktgmonoRoot>/marketing-cli` and `.../mktg-studio`. In a bare `/workspace` checkout they mark suites unreachable. Symlink `s

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads MCP configurationlowAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

4. **Optional integrations**: Postiz / Typefully / Resend / Firecrawl / Exa are BYO. Exa is first-class via skills `exa-search`, `exa-contents`, `company-research`, `lead-generation`, `build-with-exa` + root `.mcp.json`.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

6. **Studio UI vs API in cloud VMs**: Bun API on `:3001` is the source of truth. The Next dashboard on `:3000` rewrites `/api/*` → Bun; that proxy can hang (`socket hang up` / HTTP 000) while direct `:3001` curls stay he
AGENTS.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marketing Agents

[!IMPORTANT] For CLI runtime usage, read CONTEXT.md. For /cmo runtime indexes, read skills/cmo/rules/cli-runtime-index.md, skills/cmo/rules/publish-index.md, and skills/cmo/rules/studio-api-index.md. For /axi (AXI catalog router — gh-axi, chrome-devtools-axi, principles), read skills/axi/SKILL.md. For development standards, read CLAUDE.md. This file covers the 5 marketing sub-agents and the drop-in contracts for skills and agents.

6 sub-agents that /cmo spawns for parallel research and review. Installed to ~/.claude/agents/ by mktg init and mktg update.

Agent Registry

Agent Category Writes Reads skill Spawned by
mktg-brand-researcher research brand/voice-profile.md brand-voice /cmo foundation
mktg-audience-researcher research brand/audience.md audience-research /cmo foundation
mktg-competitive-scanner research brand/competitors.md competitive-intel /cmo foundation
mktg-content-reviewer review none (scores only) reads brand/voice-profile.md on demand
mktg-seo-analyst review none (scores only) reads brand/keyword-plan.md on demand

How Agents Work

  1. Registry: agents-manifest.json is the source of truth for all agent metadata.
  2. Installation: mktg init and mktg update copy agent .md files from the package to ~/.claude/agents/.
  3. Spawning: /cmo spawns all 3 research agents in a single message for maximum parallelism.
  4. Autonomy: Agents do not ask questions. They research, analyze, and write.
  5. Isolation: Agents never call other agents. /cmo orchestrates.

Security Posture

[!IMPORTANT] The agent is not a trusted operator. Assume all inputs can be adversarial.

Rule Detail
File writes Constrained to brand/, marketing/, .mktg/ via sandboxPath()
Resource IDs Reject .., absolute paths, control characters
CLI output Use --json for all calls. TTY output is for humans, JSON is the agent contract.
Mutations Use --dry-run before any mutating operation
Context window Use --fields to minimize payload size

Read the full file on GitHub · 309 lines

Changes

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.

  1. 4d ago First seen · 309 lines · 5,424 tokens per session scan B e69cc99ed1b8

Subscribe to this mod's changes

marketing-cli AGENTS.md is an instructions file published in the GitHub repository MoizIbnYousaf/marketing-cli (31 stars, last pushed 17d ago), licensed MIT. It adds 5,424 tokens to every session, about $0.0271 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.