cross-agent

A setup tool for making reusable coding-agent instructions work across Claude Code, OpenAI Codex, and GitHub Copilot.

In plain words
What is it for?
Use it to migrate repository skills, inspect existing agent configuration, and set up shared instructions such as AGENTS.md or related files.
Why use it?
It reduces duplicated instruction files and helps different coding agents use the same project guidance.

Skill for Claude CodeCodex

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 skills/drn/dots/cross-agent
Any agent
npx skills add drn/dots --skill cross-agent
Clone the repo
git clone --depth 1 https://github.com/drn/dots

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,919 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00040 $0.03919
Opus 5 $0.00020 $0.01959
Sonnet 5 $0.00008 $0.00784
Haiku 4.5 $0.00004 $0.00392

Measured 2d ago against content hash a3702bcb0fed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cross-agent scanned grade B with 1 finding 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 2d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

- Existing .claude/skills: !`find .claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30`
agents/skills/cross-agent/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Agent Skill Setup

Migrate a repository's skills to the Agent Skills open standard so they work across Claude Code, Codex, and Copilot.

Arguments

  • $ARGUMENTS - Optional: path to target repo (defaults to current working directory)

Context

  • Existing .agents/skills: !find .agents/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30
  • Existing .claude/commands: !find .claude/commands -maxdepth 1 -name "*.md" 2>/dev/null | head -30
  • Existing .claude/skills: !find .claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | head -30
  • AGENTS.md exists: !find . -maxdepth 1 -name AGENTS.md 2>/dev/null | head -1
  • CLAUDE.md type: !file CLAUDE.md 2>/dev/null | head -1
  • claude.md (lowercase) exists: !find . -maxdepth 1 -type f 2>/dev/null | grep '/claude\.md$' | head -1
  • Copilot instructions: !find .github -maxdepth 1 -name copilot-instructions.md 2>/dev/null | head -1
  • Subtree CLAUDE.md files: !find . -mindepth 2 -maxdepth 4 -name CLAUDE.md -not -path './.git/*' 2>/dev/null | head -20
  • Subtree AGENTS.md files: !find . -mindepth 2 -maxdepth 4 -name AGENTS.md -not -path './.git/*' 2>/dev/null | head -20
  • Git root: !git rev-parse --show-toplevel 2>/dev/null | head -1

Instructions

Step 0: Pre-flight

Verify this is a git repository. If not, stop and report.

If $ARGUMENTS contains a path, cd to it first.

Step 1: Discover Repo State

Scan for existing skills in all locations:

  1. .agents/skills/*/SKILL.md (already canonical)
  2. .claude/commands/*.md (Claude flat commands)
  3. .claude/skills/*/SKILL.md (Claude directory skills) Also check for a lowercase claude.md — Claude Code requires CLAUDE.md (uppercase) for discovery. Use ls -1 | grep '^claude\.md$' to detect the wrong casing (a plain test -f is unreliable on case-insensitive filesystems).

Classify the repo:

  • GREENFIELD: No skills anywhere. Create infrastructure only.
  • CLAUDE-ONLY: Skills in .claude/ but no .agents/skills/. Full migration needed.
  • PARTIAL: .agents/skills/ exists but missing infrastructure (no AGENTS.md, no Copilot instructions, no sync scripts).
  • COMPLETE: .agents/skills/ exists with all infrastructure. Run validation only.

Read the full file on GitHub · 305 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. 2d ago First seen · 305 lines · 40 tokens per session scan B a3702bcb0fed

Subscribe to this mod's changes

cross-agent is a skill published in the GitHub repository drn/dots (23 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 3,919 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens