harness-sync

A tool for comparing and synchronising AI coding-tool configurations across Claude Code, Cursor, GitHub Copilot, Codex, OpenCode, Windsurf, Gemini CLI, and Junie.

In plain words
What is it for?
Use it to inventory installed skills, instructions, and MCP settings, review differences, and sync chosen configurations.
Why use it?
It reveals differences between platforms and can copy selected configuration from one platform to the others.

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/harnessprotocol/harness-kit/harness-sync
Any agent
npx skills add harnessprotocol/harness-kit --skill harness-sync
Clone the repo
git clone --depth 1 https://github.com/harnessprotocol/harness-kit

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,123 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 $0.00106 $0.04123
Opus 5 $0.00053 $0.02062
Sonnet 5 $0.00021 $0.00825
Haiku 4.5 $0.00011 $0.00412

Measured 2d ago against content hash 3f931cedbdfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

harness-sync 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Codex, Windsurf: no project-level file exists for either (Codex uses `~/.codex/config.toml`, Windsurf uses a global config) — report their MCP row as `(global-only, not scanned)` rather than `(none)`, since `(none)` wo
plugins/harness-share/skills/harness-sync/SKILL.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Harness Configurations Across Platforms

You are syncing AI tool configurations across any combination of the 8 supported targets: Claude Code, Cursor, GitHub Copilot, Codex, OpenCode, Windsurf, Gemini CLI, and Junie. You will inventory what is installed and configured on each platform, report any divergence, and execute the sync direction the user chooses.

This skill depends on harness-compile: the push path reuses harness-compile's compilation logic to write the selected source platform's content to all target platforms.

Workflow Order (MANDATORY)

Follow these steps in order. Do not skip any step.


Step 1: Detect platforms

Check for any --target <platform> flag the user passed. If present, restrict the entire workflow to that platform only. Valid values: claude-code, cursor, copilot, codex, opencode, windsurf, gemini, junie. For sync, --target <platform> means "treat this platform as the only target for push output." It does not restrict which platforms are scanned in Step 2 — all detected platforms are still inventoried so divergence can be identified.

Otherwise, scan the working directory for platform indicators:

Claude Code is present if any of these exist: CLAUDE.md, .claude/, .mcp.json Cursor is present if any of these exist: .cursor/, .cursor/rules/, .cursor/mcp.json, .cursor/skills/ Copilot is present if any of these exist: .github/, .vscode/mcp.json, .github/skills/ Codex is present if .codex/ exists OpenCode is present if opencode.json or .opencode/ exists Windsurf is present if .windsurf/ exists Gemini CLI is present if .gemini/ exists Junie is present if .junie/ exists

Never assume a platform is present. Detect each independently. If .github/ is the only Copilot indicator, ask the user:

"I found a .github/ directory but no other Copilot indicators. Are you using GitHub Copilot in this project?"

A bare AGENTS.md with none of the tool-specific directories above is ambiguous — it's the shared instruction file for Codex, OpenCode, Windsurf, Gemini CLI, and Junie, so its presence alone doesn't identify which one. Ask which of those five the user actually uses rather than assuming or offering all of them.

Read the full file on GitHub · 323 lines

Files

What ships with it

1 file 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. 2d ago First seen · 323 lines · 106 tokens per session scan B 3f931cedbdfc

Subscribe to this mod's changes

harness-sync is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 106 tokens to every session and 4,123 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

studio

Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.

AlpacaLabsLLC/skills-for-architects · 65 tokens

epd-to-spec

Write CSI specification language for EPD submittals and sourced GWP limits. Use to add embodied-carbon or EPD requirements to specs; not to parse, find, or compare EPDs.

AlpacaLabsLLC/skills-for-architects · 45 tokens

occupancy-calculator

Calculate code occupant loads by area with gross/net factors and jurisdiction checks. Use for "how many people can this space hold," IBC Table 1004.5, egress inputs, or occupancy-load reports; not for workplace headcount planning.

AlpacaLabsLLC/skills-for-architects · 55 tokens

zoning-analysis-nyc

Analyze NYC lot zoning, FAR, height, setbacks, uses, and buildable envelope from PLUTO and the Zoning Resolution. Use for "what can I build"; use nyc-bsa for relief and zoning-envelope for 3D visualization.

AlpacaLabsLLC/skills-for-architects · 57 tokens

spec-writer

Turn a material or product list into CSI MasterFormat outline specifications with three-part sections and review flags. Use to write specs; use epd-to-spec for embodied-carbon requirements.

AlpacaLabsLLC/skills-for-architects · 39 tokens

workplace-programmer

Build office space programs through guided workplace strategy: area splits, room schedules, and planned seat counts. Use to program or size a workplace; not for code occupant-load calculations.

AlpacaLabsLLC/skills-for-architects · 40 tokens