What is harness-sync?

A tool for copying a working Claude Code setup to another computer or repository and checking whether the setups have drifted apart. Claude Code is a coding assistant that uses local configuration, plugins, and instructions.

Use it when setting up a second machine, onboarding a laptop, recovering configuration, reinstalling plugin marketplaces, or comparing two setups.

It avoids copying sensitive machine-specific files such as credentials, logs, caches, and tokens along with the reusable setup.

harness-sync — Skill for Claude Code by ondrej-svec

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.

Any agent

npx skills add ondrej-svec/heart-of-gold-toolkit --skill harness-sync

Clone the repo

git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code.

Or install marvin, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks.

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/skills/ondrej-svec/heart-of-gold-toolkit/harness-sync/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/harness-sync)

Your own site

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/harness-sync"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/harness-sync/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/skills/ondrej-svec/heart-of-gold-toolkit/harness-sync"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/harness-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,789 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00109	$0.01789
Opus 5.5	$0.00044	$0.00716
Sonnet 5.5	$0.00022	$0.00358
Haiku 4.5	$0.00011	$0.00179

Measured 2mo ago against content hash 6958ffd603b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-sync 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.

plugins/marvin/skills/harness-sync/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Sync

Move a working Claude Code harness to a second machine, and keep the two from drifting apart afterwards.

Distinct from its siblings: marvin:harness-up writes doctrine into a target repo (AGENTS.md, docs taxonomy). marvin:scaffold installs dependencies and configs. This skill replicates the harness itself — ~/.claude.

Boundaries

This skill MAY: clone or pull the user's config repo, read local config, run claude plugin install commands, run the harness validator, report drift.

This skill MAY NOT: push to any remote, commit on the user's behalf, write credentials, overwrite an existing ~/.claude without explicit confirmation, or copy machine-local state (logs, auto memory, plugin caches, tokens).

Common Rationalizations

Shortcut	Why It Fails	The Cost
"Just rsync the whole `~/.claude`"	Carries credentials, logs, plugin caches and per-machine auto memory	Tokens leak onto a second machine; caches for the wrong architecture
"Clone over the existing config, it's probably the same"	It usually is not, and the delta is invisible after the fact	Local-only skills and hooks destroyed with no record
"Config is tracked, so the machines match"	Plugins install out-of-band; a tracked settings.json can name marketplaces that were never added here	Skills silently missing, hooks referencing plugins that aren't installed
"Skip validation, the repo was fine on the other machine"	Absolute paths, missing binaries and unexecutable scripts are all machine-specific	A harness that looks installed and silently no-ops

Phase 0: Detect Mode

Entry: Skill invoked, optionally with check, install, or drift.

Resolve the mode:

Signal	Mode
Argument given	Use it
`~/.claude/.git` absent	`install` — nothing here yet
`~/.claude/.git` present, argument absent	`check`

If install and ~/.claude already contains un-tracked local work, stop and ask via AskUserQuestion before touching anything.

Read the full file on GitHub · 196 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 · 196 lines · 109 tokens per session scan A 6958ffd603b4

Subscribe to this mod's changes

harness-sync is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,789 once invoked, about $0.0004 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.

Building agents

harness-sync next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-syncondrej-svec/heart-of-gold-toolkit	Skill	19	1mo ago	MIT	A	109	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code