adaptico-os AGENTS.md

A set of instructions for an AI coding assistant working in Adaptico OS, a command-line system that helps early-stage software founders with marketing and sales tasks.

In plain words
What is it for?
It guides website marketing reviews, positioning work, conversion improvements, copywriting, launch planning, and competitor analysis.
Why use it?
It gives the assistant the project context, workspace layout, and expected output format, so its work follows the repository's intended process.

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

Made for: Codex, OpenCode.

Per session 1,890 This file is loaded in full into every session.
When invoked 1,890 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 $0.01890 $0.01890
Opus 5 $0.00945 $0.00945
Sonnet 5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 3d ago against content hash 6b986ceeecdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adaptico-os 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 3d 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 · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adaptico OS — Operating Instructions

This file is loaded automatically by Claude Code, Cursor, Windsurf, Codex, and any other AI tool running in this workspace. It defines what Adaptico OS is and how to work in this repository.


What This Is

Adaptico OS is a go-to-market operating system for early-stage SaaS and AI startup founders, built on Claude Code skills. A founder "plugs in" their project and gets deep, specific go-to-market help from the command line: audit the website's marketing, sharpen positioning, fix conversion, generate copy, plan a launch, and analyze competitors. The default user is a technical founder marketing a modern software product.


Workspace Structure

adaptico-os/
├── src/                  ← all installable sources (the only thing the installers copy)
│   ├── core/             ← public/free edition
│   │   ├── skills/       ← gtm orchestrator (bundles its own scripts/ + templates/) + core skills (gtm-*)
│   │   └── agents/       ← 5 parallel audit subagents (gtm-*)
├── projects/             ← per-project work
├── .claude/              ← generated by install.sh
├── install.sh / uninstall.sh
├── AGENTS.md             ← this file
├── CLAUDE.md             ← points here
├── LICENSE  /  CREDITS.md

How a Founder Uses It

  1. Install the skills into their own workspace - as the Claude Code plugin (recommended), via npx skills add, or with ./install.sh from a clone (the README's install section documents the full order).
  2. Run /gtm init to create a projects/<project-name>/PROFILE.md describing their project (URL, type, stage, ICP, goal, competitors), plus a LOG.md history of what's been tried and what happened - every command run appends its outcome line to it, in per-channel sections.
  3. Run commands against their own site — e.g. /gtm audit, /gtm position, /gtm landing.
  4. Reports save to the project directory (projects/<project-name>/) with a YYYY-MM-DD- prefix.

PROFILE.md is the single source of truth for the project. Read it (when present) before any analysis and tailor tone, focus, and recommendations to the stated type, stage, ICP, and goal.

Read the full file on GitHub · 114 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. 3d ago First seen · 114 lines · 1,890 tokens per session scan A 6b986ceeecdf

Subscribe to this mod's changes

adaptico-os AGENTS.md is an instructions file published in the GitHub repository adaptico/adaptico-os (16 stars, last pushed 16d ago), licensed MIT. It adds 1,890 tokens to every session, about $0.0095 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.

Related

Other instructions, from other repositories