What is cc-mirror AGENTS.md?

A repository guide that explains a project's folders, commands, coding rules, build and test process, and configuration flow. It is written for coding agents working in that repository.

Use it when developing, testing, building, or navigating the cc-mirror repository, especially when working across its command-line interface, terminal user interface, and core code.

It gives an agent the project-specific information it needs to make changes without guessing how the code is organized or validated.

How numman-ali/cc-mirror configures Codex and OpenCode

About the project

CC-MIRROR is a distribution that creates separate Claude Code variants configured to use providers such as Z.ai, MiniMax, OpenRouter, and LiteLLM. It is for people who want provider-specific coding setups with predefined prompts and settings. The catalogue entries provide instructions for using or managing these variants.

numman-ali/cc-mirror · 2,260 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to numman-ali/cc-mirror. 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/numman-ali/cc-mirror/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/numman-ali/cc-mirror

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/numman-ali/cc-mirror/agents-md/github.svg)](https://agentmods.dev/instructions/numman-ali/cc-mirror/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/numman-ali/cc-mirror/agents-md"><img src="https://agentmods.dev/badge/instructions/numman-ali/cc-mirror/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/numman-ali/cc-mirror/agents-md"><img src="https://agentmods.dev/badge/instructions/numman-ali/cc-mirror/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,792 This file is loaded in full into every session.

When invoked 2,792 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	$0.02792	$0.02792
Opus 5.5	$0.01117	$0.01117
Sonnet 5.5	$0.00558	$0.00558
Haiku 4.5	$0.00279	$0.00279

Measured 2mo ago against content hash 0394d1f6d5ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cc-mirror 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 · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure

src/
├── cli/                    # CLI entrypoint and commands
│   ├── index.ts           # Main CLI entry
│   ├── commands/          # create, update, remove, doctor, etc.
│   └── args.ts            # Argument parsing
├── tui/                    # Ink-based TUI wizard
│   ├── app.tsx            # Main TUI application
│   ├── screens/           # Individual screen components
│   ├── components/        # Reusable UI components
│   ├── hooks/             # React hooks for business logic
│   ├── state/             # State types and management
│   └── router/            # Screen navigation
├── core/                   # Core variant management
│   ├── index.ts           # Public API (createVariant, updateVariant, etc.)
│   ├── variant-builder/   # Step-based variant creation
│   │   ├── VariantBuilder.ts
│   │   ├── VariantUpdater.ts
│   │   ├── steps/         # Build steps (PrepareDirectories, InstallNative, etc.)
│   │   └── update-steps/  # Update steps
│   ├── prompt-pack/       # System prompt overlays
│   │   ├── providers/     # Per-provider overlays (zai.ts, minimax.ts)
│   │   ├── overlays.ts    # Overlay resolution
│   │   └── targets.ts     # Target file mapping
│   └── *.ts               # Utils (paths, fs, tweakcc, skills, etc.)
├── providers/              # Provider templates
│   └── index.ts           # Provider definitions and defaults
├── brands/                 # TweakCC brand presets
│   ├── index.ts           # Brand resolution
│   ├── types.ts           # TweakCC config types
│   ├── zai.ts             # Z.ai theme + blocked tools
│   ├── minimax.ts         # MiniMax theme + blocked tools
│   └── *.ts               # Other brand configs

test/                       # Node test runner tests
├── e2e/                   # End-to-end tests
├── tui/                   # TUI component tests
├── unit/                  # Unit tests
└── helpers/               # Test utilities

repos/                      # Upstream reference copies (vendor data, history)
├── anthropic-claude-code-*/       # Claude Code versions for comparison/reference
├── claude-code-system-prompts/    # System prompt changelog and sources
└── tweakcc/                       # TweakCC repo (prompt patching tool)

notes/                      # Research notes and deep dive documentation
├── CLI-VERSIONS.md               # Version comparison notes
├── *-DEEP-DIVE.md                # Feature research and analysis
└── RECONSTRUCTION-LEDGER.md      # Project state and decisions

docs/                       # User documentation
dist/                       # Build output (generated)

Read the full file on GitHub · 297 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 · 297 lines · 2,792 tokens per session scan A 0394d1f6d5ce

Subscribe to this mod's changes

cc-mirror AGENTS.md is an instructions file published in the GitHub repository numman-ali/cc-mirror (2,260 stars, last pushed 5mo ago), licensed MIT. It adds 2,792 tokens to every session, about $0.0112 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.

cc-mirror AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cc-mirror AGENTS.mdnumman-ali/cc-mirror	Instructions file	2.3k	5mo ago	MIT	A	2,792	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	today	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

cc-mirror: Instructions file for Codex