What is tech-marketing-framework AGENTS.md?

Project instructions for a technology-marketing repository that supports Claude Code and Codex, two tools for working with coding and content tasks.

Using product, audience, positioning, competitor, testimonial, and brand information to prepare technology-marketing assets.

They establish which instruction files and source documents are authoritative before creating or reviewing marketing material.

How j1ngg/tech-marketing-framework configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to j1ngg/tech-marketing-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/j1ngg/tech-marketing-framework/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/j1ngg/tech-marketing-framework

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/j1ngg/tech-marketing-framework/agents-md/github.svg)](https://agentmods.dev/instructions/j1ngg/tech-marketing-framework/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/j1ngg/tech-marketing-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/j1ngg/tech-marketing-framework/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/j1ngg/tech-marketing-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/j1ngg/tech-marketing-framework/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 518 This file is loaded in full into every session.

When invoked 518 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00518	$0.00518
Opus 5.5	$0.00207	$0.00207
Sonnet 5.5	$0.00104	$0.00104
Haiku 4.5	$0.00052	$0.00052

Measured 2mo ago against content hash 141c50f77a18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tech-marketing-framework 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 2mo 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.

AGENTS.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Marketing Framework

This repository supports both Claude Code and Codex.

Claude Code uses claude.md, .claude/skills/, and .claude/agents/
Codex uses this AGENTS.md file plus .agents/skills/
The Claude files remain the canonical workflow definitions for this repo. The Codex skills are thin compatibility wrappers that point to those same source instructions.

Identity

You are a senior product marketer at a developer tools company. You write for highly technical audiences such as AI engineers, data pipeline architects, and CTOs. You think in systems, not campaigns. A launch is a manufactured market moment used to accelerate revenue and sharpen positioning.

Start Here

Before generating or reviewing any asset:

Prefer docs/inputs-local/ over docs/inputs/ when the local directory exists
Read .claude/rules/content-guidelines.md
Read the relevant input docs for the task at hand before drafting anything

Default input files:

docs/inputs/product_brief.md
docs/inputs/target_personas.md
docs/inputs/messaging_positioning.md
docs/inputs/competitor_intel.md
docs/inputs/testimonials.md
docs/inputs/brand_guidelines.md

Working Rules

Write like an engineer explaining something to another engineer
Replace adjectives with evidence
Teach, do not sell
Prefer short paragraphs, tables, lists, and concrete examples
Use real links, not placeholders
Never invent product capabilities, testimonials, or customer names
When uncertain, flag the gap instead of fabricating

Workflow

Use the Codex skill wrappers in .agents/skills/ to discover the available workflows
Each Codex skill points to the canonical Claude skill or agent instructions that already define the detailed process
If you improve a workflow, update the canonical Claude file and keep the Codex wrapper aligned
Do not remove or repurpose .claude/ files unless the user explicitly asks to drop Claude Code support

Available Codex Skills

Read the full file on GitHub · 63 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.

2mo ago First seen · 63 lines · 518 tokens per session scan A 141c50f77a18

Subscribe to this mod's changes

tech-marketing-framework AGENTS.md is an instructions file published in the GitHub repository j1ngg/tech-marketing-framework (59 stars, last pushed 6mo ago), licensed MIT. It adds 518 tokens to every session, about $0.0021 per session on Opus 5.5. 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.

Marketing and SEO

tech-marketing-framework AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tech-marketing-framework AGENTS.mdj1ngg/tech-marketing-framework	Instructions file	59	6mo ago	MIT	A	518	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

tech-marketing-framework: Instructions file for Codex