What is claude-code-profiles AGENTS.md?

A repository instruction file for Claude Code, a coding agent, describing a project that manages separate configuration profiles. It documents the project layout, supported shells, commands, and how the profile wrapper selects a configuration.

Use it when changing profile management, shell implementations, command interfaces, or directory-local agent instructions in this project.

It gives an agent the local rules and architecture it needs before editing this repository, reducing the chance of breaking shell-specific behaviour.

How quinnjr/claude-code-profiles configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to quinnjr/claude-code-profiles. 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/quinnjr/claude-code-profiles/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/quinnjr/claude-code-profiles

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/quinnjr/claude-code-profiles/agents-md/github.svg)](https://agentmods.dev/instructions/quinnjr/claude-code-profiles/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/quinnjr/claude-code-profiles/agents-md"><img src="https://agentmods.dev/badge/instructions/quinnjr/claude-code-profiles/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/quinnjr/claude-code-profiles/agents-md"><img src="https://agentmods.dev/badge/instructions/quinnjr/claude-code-profiles/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,861 This file is loaded in full into every session.

When invoked 1,861 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	$0.01861	$0.01861
Opus 5.5	$0.00744	$0.00744
Sonnet 5.5	$0.00372	$0.00372
Haiku 4.5	$0.00186	$0.00186

Measured 1mo ago against content hash c52c56c0da04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-profiles 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 1mo 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 · 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.

AGENTS.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

Cross-platform shell functions for managing multiple Claude Code configuration profiles via CLAUDE_CONFIG_DIR. Each profile is a complete, isolated config directory. A transparent claude() wrapper auto-resolves the active profile so users just run claude normally.

Three equivalent implementations: POSIX sh (sourced), PowerShell (dot-sourced), and Windows cmd batch.

Architecture

The POSIX and PowerShell implementations are sourceable function files (not standalone scripts). They each define two functions: claude() (transparent wrapper) and claude-profile() (management). The cmd batch script is standalone since cmd lacks a function-sourcing mechanism.

claude-profile.sh (POSIX sh) — reference implementation. Sourced in .bashrc/.zshrc. Provides claude() wrapper that auto-resolves the default profile before calling the real binary via command claude. Provides claude-profile() for management commands. Strict POSIX only: no local, no [[ ]], no arrays, no bashisms. Uses printf over echo, _cp_-prefixed variables, return (not exit — runs in user's shell). On Git Bash / MSYS2 (detected via $MSYSTEM), profiles are stored at %LOCALAPPDATA%\claude-profiles\ and paths are converted via cygpath -w before invoking claude.exe so they are shared with the cmd/PowerShell implementations.
claude-profile-init.ps1 (PowerShell 5.1+/pwsh 6+) — cross-platform. Dot-sourced in $PROFILE. Same two-function model. Uses $args manual parsing (not param()) to avoid conflicts with PowerShell parameter binding. Get-Command -CommandType Application to find the real claude binary past the function.
claude-profile.cmd (Windows batch) — standalone script. Uses goto :label dispatch, setlocal enabledelayedexpansion, endlocal & set idiom to leak CLAUDE_CONFIG_DIR to the caller. No transparent claude wrapper (cmd limitation). Users run call claude-profile.cmd use <name> then claude separately.

Read the full file on GitHub · 106 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.

1mo ago First seen · 106 lines · 1,861 tokens per session scan A c52c56c0da04

Subscribe to this mod's changes

claude-code-profiles AGENTS.md is an instructions file published in the GitHub repository quinnjr/claude-code-profiles (99 stars, last pushed 1mo ago), licensed MIT. It adds 1,861 tokens to every session, about $0.0074 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 2026-09-19.

Building agents anthropic claude cli configuration cross-platform

claude-code-profiles AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-profiles AGENTS.mdquinnjr/claude-code-profiles	Instructions file	99	1mo ago	MIT	A	1,861	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-code-profiles: Instructions file for Codex