Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Agnostic Repo Mirror

ASecurity

Use when one repo must serve Claude, Codex, and other harnesses from a single canonical config without duplicated rules. Triggers on \"agnostic repo\", \"same brain\", \"AGENTS.md canonical\", \"claude code and codex\", \"skills symlink\", \"drift audit\". Non-triggers: memory handoff between agents (use unified-memory). Outcome: AGENTS.md as source of truth with thin per-harness imports, linked skills dir, and a passing drift audit.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgo

Works with

claude code

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill agnostic-repo-mirror --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agnostic Repo Mirror?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Agnostic Repo Mirror
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-agnostic-repo-mirror/badge)](https://www.skillsdirectory.com/skills/majinmagros-agnostic-repo-mirror)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: agnostic-repo-mirror
description: "Use when one repo must serve Claude, Codex, and other harnesses from a single canonical config without duplicated rules. Triggers on \"agnostic repo\", \"same brain\", \"AGENTS.md canonical\", \"claude code and codex\", \"skills symlink\", \"drift audit\". Non-triggers: memory handoff between agents (use unified-memory). Outcome: AGENTS.md as source of truth with thin per-harness imports, linked skills dir, and a passing drift audit."
metadata:
  origin: ECC
---

# Agnostic Repo Mirror

One repo, many harnesses. Keep `AGENTS.md` as the canonical source of
truth, shrink `CLAUDE.md` to a thin import, serve one shared skills
directory through a link, and audit drift on a schedule. File-level
mirror, not memory handoff: `unified-memory` moves context between
agents, this skill keeps the repo surfaces identical.

## When To Activate

- The user says same brain, stop choosing between harnesses, Claude
  plus Codex, repo agnostic, or skills in two places.
- Rules live in both `CLAUDE.md` and `AGENTS.md` and already disagree.
- Skills are duplicated under per-harness folders and fixes land in
  only one copy.
- A team adds a second harness to a repo that was Claude-only.

## Layout

```text
repo/
|-- AGENTS.md             # canonical rules, edit here
|-- CLAUDE.md             # thin import, do not extend
|-- .agents/
|   `-- skills/           # canonical skills
`-- .claude/
    `-- skills -> ../.agents/skills   # link, not a copy
```

- Canonical content lives in exactly one place. Every other surface
  imports or links to it.
- No rule text is typed twice. Duplicated text is drift waiting to
  happen.

## Workflow

### 1. Promote AGENTS.md to canon

- Move all durable rules into `AGENTS.md`: identity, routing, model
  policy, tool policy, style, done criteria.
- Delete harness-specific paths from the canon. Keep generic tokens
  like `<repo>` and `<skills-dir>` instead of per-tool paths.
- Commit the canon before touching any import.

### 2. Shrink CLAUDE.md to an import

- Reduce `CLAUDE.md` to a short header plus one import line pointing
  at the canon:

```text
@AGENTS.md
```

- Keep at most a small Claude-only appendix below the import for
  genuinely Claude-only behavior. Anything shared moves up.
- Rule: edits to shared behavior go to `AGENTS.md`, never to the
  appendix.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →