agent-adapters

agent-adapters is a skill for Claude Code, Codex from kok-o/koko-contextos-agents. It costs 46 tokens per session (680 once invoked), scanned A, original, MIT.

A configuration generator that converts one shared project instruction format into files understood by different coding agents, such as Claude Code, Cursor, Copilot, and Aider.

In plain words
What is it for?
It is for generating configuration files for one supported agent or all supported agents from the shared ContextOS project information.
Why use it?
It avoids rewriting the same project rules separately for every coding tool.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions CLAUDE.md; mentions Claude Code; installed under .agents/ (shared by several agents).

Good fit It is for generating configuration files for one supported agent or all supported agents from the shared ContextOS project information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kok-o/koko-contextos-agents/adapters
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.

Any agent
npx skills add kok-o/koko-contextos-agents --skill adapters
Clone the repo
git clone --depth 1 https://github.com/kok-o/koko-contextos-agents

Made for: Claude Code, Codex.

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 agent-adapters

README.md
[![agentmods](https://agentmods.dev/badge/skills/kok-o/koko-contextos-agents/adapters/github.svg)](https://agentmods.dev/skills/kok-o/koko-contextos-agents/adapters)
Your own site
<a href="https://agentmods.dev/skills/kok-o/koko-contextos-agents/adapters"><img src="https://agentmods.dev/badge/skills/kok-o/koko-contextos-agents/adapters/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.

agentmods 80×15 button for agent-adapters

Your own site · 80×15
<a href="https://agentmods.dev/skills/kok-o/koko-contextos-agents/adapters"><img src="https://agentmods.dev/badge/skills/kok-o/koko-contextos-agents/adapters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00680
Opus 5 $0.00023 $0.00340
Sonnet 5 $0.00009 $0.00136
Haiku 4.5 $0.00005 $0.00068

Measured 9d ago against content hash eca2ed9fd839, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-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 9d 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/core/skills/adapters/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 · 106 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 106 lines · 46 tokens per session scan A eca2ed9fd839

Subscribe to this mod's changes

agent-adapters is a skill published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 680 once invoked, about $0.0002 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.