adapters

adapters is a cursor rule for Cursor from kok-o/koko-contextos-agents. It costs 5 tokens per session (650 once invoked), scanned A, original, MIT.

A ruleset for generating configuration files that give different AI coding agents project instructions. It supports formats used by agents such as Claude Code, Cursor, Aider, Continue, OpenHands, and Windsurf.

In plain words
What is it for?
Use it to create configuration for one agent or all supported agents from shared project documentation and architecture information.
Why use it?
Different agents expect instructions in different files and formats. These rules describe how to produce the appropriate configuration for each supported agent.

Cursor rule for Cursor

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 rules/kok-o/koko-contextos-agents/adapters
Clone the repo
git clone --depth 1 https://github.com/kok-o/koko-contextos-agents

Made for: Cursor.

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 adapters

README.md
[![agentmods](https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/adapters.svg)](https://agentmods.dev/rules/kok-o/koko-contextos-agents/adapters)
Your own site
<a href="https://agentmods.dev/rules/kok-o/koko-contextos-agents/adapters"><img src="https://agentmods.dev/badge/rules/kok-o/koko-contextos-agents/adapters.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00005 $0.00650
Opus 5 $0.00003 $0.00325
Sonnet 5 $0.00001 $0.00130
Haiku 4.5 $0.00001 $0.00065

Measured 4d ago against content hash dd0130d4b44b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adapters 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 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.

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.

.cursor/rules/adapters.mdc · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: adapters

agent-adapters

Overview

A brief summary of what the skill does and its core philosophy.

When to Use

Context for when this skill is applicable.

Rules & Patterns

ContextOS is agent-agnostic. This skill generates the right config format for any AI agent.

Supported Agents

Agent Config File Format
Gemini .agents/AGENTS.md + .agents/skills/ Markdown + YAML skills
Claude Code CLAUDE.md Single markdown file
GitHub Copilot / Codex AGENTS.md (root) Markdown
Cursor .cursorrules Plain text rules
Aider .aider.conf.yml YAML config
Continue .continuerules Markdown rules
OpenHands openhands.json JSON config
Roo Code .roo/ Directory with rules
Windsurf .windsurfrules Plain text rules

Generation Command

ctx adapt [agent] — Generate config for a specific agent.

ctx adapt all — Generate configs for all supported agents.

Adapter Logic

For Claude Code (CLAUDE.md)

Compile into a single markdown file:

  1. Project overview from docs/PRD.md (summary only)
  2. Architecture summary from docs/ARCHITECTURE.md
  3. Coding rules from loaded skills
  4. Active Decision Records
  5. Current tasks from docs/TASKS.md

For Gemini (.agents/AGENTS.md)

Already native format. Just ensure:

  1. AGENTS.md references the skill directory
  2. Skills have proper SKILL.md with frontmatter
  3. Context Manager rules are in AGENTS.md

For Cursor (.cursorrules)

Compile into a flat text file:

  1. Project context (condensed)
  2. Coding style rules
  3. Framework-specific instructions
  4. Anti-patterns to avoid

For Aider (.aider.conf.yml)

read:
  - docs/ARCHITECTURE.md
  - docs/API.md
  - docs/PROJECT_GRAPH.md
conventions:
  - {{coding rules from skills}}

Sync Rules

  • Adapters read from the canonical ContextOS documents
  • Never edit adapter output files directly
  • Re-run ctx adapt after any document change
  • Each adapter file includes a header: # Generated by ContextOS — do not edit directly

Read the full file on GitHub · 107 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 · 107 lines · 5 tokens per session scan A dd0130d4b44b

Subscribe to this mod's changes

adapters is a cursor rule published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 5 tokens to every session and 650 once invoked, about $0.0000 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 2026-08-31.