taketomarket AGENTS.md

taketomarket AGENTS.md is an instructions file for Codex, OpenCode from ranjanrishikesh/taketomarket. It costs 3,260 tokens per session, scanned A, original, MIT.

A Codex skill that applies specification-driven development ideas to marketing. It treats campaigns and marketing materials as planned units with measurable outcomes and quality checks.

In plain words
What is it for?
Use it to plan and run marketing campaigns, define positioning and target customers, create marketing materials, track outcomes, and check work against set quality rules.
Why use it?
It gives engineers and solo product builders a structured way to handle marketing when they have little experience with it.

Instructions file for CodexOpenCode

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/ranjanrishikesh/taketomarket/agents-md
Clone the repo
git clone --depth 1 https://github.com/ranjanrishikesh/taketomarket

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 taketomarket AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ranjanrishikesh/taketomarket/agents-md.svg)](https://agentmods.dev/instructions/ranjanrishikesh/taketomarket/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ranjanrishikesh/taketomarket/agents-md"><img src="https://agentmods.dev/badge/instructions/ranjanrishikesh/taketomarket/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,260 This file is loaded in full into every session.
When invoked 3,260 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.03260 $0.03260
Opus 5 $0.01630 $0.01630
Sonnet 5 $0.00652 $0.00652
Haiku 4.5 $0.00326 $0.00326

Measured 5d ago against content hash 22730fe6f737, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

taketomarket AGENTS.md 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project

takeToMarket

An open-source Codex / Codex skill that brings GSD-style spec-driven development to marketing. takeToMarket is a marketing operating system — not a content generator — that treats every campaign, asset, and channel as a spec-driven unit with a verifiable outcome, a positioning invariant, and a quality gate wall. Users install it into their Codex or Codex environment and run marketing campaigns through a 9-phase lifecycle with persistent state, compound learnings, and automated verification.

Core Value: Every marketing asset ships with a verifiable outcome metric and passes through a positioning-invariant quality gate wall — no asset ships without both, ever.

Target Audience

Built for developerneurs and solopreneurs — engineers building and shipping their own products who have zero or near-zero marketing/growth experience.

When assisting the user:

  • Assume strong engineering literacy. They read code fluently.
  • Assume zero marketing literacy. Explain positioning, ICP, AEO, funnels in engineering analogies.
  • Default to opinionated guidance — they came here because they don't know what's "right" in marketing.
  • When suggesting marketing terms, link to /ttm-101 or run inline explanations on first use.

Constraints

  • Platform: Must work as a Codex skill AND Codex skill — skill format must be compatible with both runtimes
  • Context window: Production in Produce phase uses fresh 200K-token contexts per wave, loaded with brief + positioning + brand + ICP + playbook
  • No external dependencies for MVP: The skill itself should not require external services — analytics data is pasted in manually
  • State persistence: All state lives in .taketomarket/ directory files — no database, no external storage

Technology Stack

Core Technologies

Technology Version Purpose Why Recommended
SKILL.md (Agent Skills standard) Current Skill entry point and slash command definition Universal standard adopted by Codex, Codex, Gemini CLI, Cursor, and 8+ runtimes. Each SKILL.md directory becomes a /ttm-* slash command. Verified via official Codex docs.
AGENTS.md Current Project-level instruction file for Codex Loaded automatically in every session. takeToMarket uses this to inject positioning-as-invariant enforcement and campaign lifecycle rules.
AGENTS.md Current Codex-compatible instruction file Codex reads AGENTS.md automatically. Coexists with AGENTS.md -- both can live in the same repo. Required for dual-runtime support.
Markdown (.md) N/A All skill content, templates, workflows, references The entire Codex skill ecosystem is Markdown-native. YAML frontmatter for config, Markdown body for instructions. No other format is viable.
Node.js (CJS) 18+ CLI utilities (bin/ tools) GSD uses .cjs files for deterministic operations (state management, config parsing, slug generation, commit orchestration). Node 18+ is required by Codex itself.
YAML frontmatter N/A Skill metadata, plan metadata, state tracking Standard across all Agent Skills. Parsed natively by Codex, Codex, and the GSD ecosystem.

Read the full file on GitHub · 188 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. 5d ago First seen · 188 lines · 3,260 tokens per session scan A 22730fe6f737

Subscribe to this mod's changes

taketomarket AGENTS.md is an instructions file published in the GitHub repository ranjanrishikesh/taketomarket (16 stars, last pushed 3mo ago), licensed MIT. It adds 3,260 tokens to every session, about $0.0163 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 2026-08-30.