What is harness-config-sync?

A configuration tool that keeps prompts and skills in one standard location while linking them into several coding-agent hosts.

It helps manage user-level or project-level agent prompts and skills for Codex, CodeBuddy, Claude Code, Kiro, Kimi Code, and Antigravity CLI.

It prevents the same configuration from being copied and becoming inconsistent across tools. It also checks and safely migrates existing local configuration.

harness-config-sync — Skill for Claude Code and Codex by hxy91819

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 hxy91819/mason-skills --skill harness-config-sync

Clone the repo

git clone --depth 1 https://github.com/hxy91819/mason-skills

Made for: Claude Code, Codex.

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/hxy91819/mason-skills/harness-config-sync/github.svg)](https://agentmods.dev/skills/hxy91819/mason-skills/harness-config-sync)

Your own site

<a href="https://agentmods.dev/skills/hxy91819/mason-skills/harness-config-sync"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/harness-config-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/hxy91819/mason-skills/harness-config-sync"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/harness-config-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,563 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00044	$0.04563
Opus 5.5	$0.00018	$0.01825
Sonnet 5.5	$0.00009	$0.00913
Haiku 4.5	$0.00004	$0.00456

Measured 19d ago against content hash 380fe18edb00, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

harness-config-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 19d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/sync_project_agent_skills.py, tests/test_sync_project_agent_skills.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

- agy（Antigravity CLI）project 级原生读取上述标准路径；user 级只在 `~/.gemini/config/` 保留两条软链接入，不建其他镜像。

common-skills/harness-config-sync/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Config Sync

一次调用完成盘点、迁移、链接和验证。不要把 check、apply、migrate 暴露成连续的用户决策；显式调用已授权在请求范围内执行可逆的本地文件迁移。只有同名实体内容无法安全合并时才停止并请用户裁决。

收敛目标

用户级事实源：prompt 为 ~/.agents/AGENTS.md，skills 为 ~/.agents/skills/。mason-skills checkout 存在时，user prompt 正文托管于该仓库的 config/user-agents.md，~/.agents/AGENTS.md 软链到它，编辑即改仓库文件，经 Git 在各环境间收敛；无 checkout 时维持普通文件现状。
项目级事实源：prompt 为仓库根 AGENTS.md，skills 为 .agents/skills/。
CodeBuddy、Claude Code、Kiro 的专有入口只保留软链；CodeBuddy 的独立个人规则可继续放在 ~/.codebuddy/rules/。
Kimi Code 原生读取上述标准 prompt 和 skills，不为同一内容创建 $KIMI_CODE_HOME 或 .kimi-code 镜像。
agy（Antigravity CLI）project 级原生读取上述标准路径；user 级只在 ~/.gemini/config/ 保留两条软链接入，不建其他镜像。
Devin project 级与 user skills 原生读取上述标准路径；user prompt 经 ~/.config/devin/AGENTS.md 软链接入，不建 .devin/ 或 .windsurf/ 镜像。
Amp project 级与 user skills 原生读取上述标准路径；user prompt 经 ~/.config/amp/AGENTS.md 软链接入。不要同时创建 ~/.config/AGENTS.md 或 ~/.config/amp/skills，Amp 会把这两处与标准路径一并注入。不建项目 .amp/AGENTS.md 或 .amp/skills 镜像。
内容只在事实源编辑。同步只治理布局，不改 Skill 正文、调用策略、仓库业务文档、Git 历史或 submodule 状态。

自动确定范围

按用户原话推断，不额外询问：

提到全局、用户级、home 或 ~/：处理 user scope。
提到仓库、项目级或当前项目：处理当前 Git 仓库。
明确提到两者或全部：两者都处理。
未指定时，在 Git 仓库内只处理当前项目；否则只处理 user scope。

只配置用户点名的宿主；用户泛指“各 Agent”时处理当前已安装或已有配置目录的 Codex、CodeBuddy、Claude Code、Kiro、Kimi Code、agy、Pi（存在 pi 可执行文件或 ~/.pi/agent/ 即视为已安装）、Devin（存在 devin 可执行文件或 ~/.config/devin/ 即视为已安装）、Amp（存在 amp 可执行文件或 ~/.config/amp/ 即视为已安装）和 DSH（存在 dsh 可执行文件或 ~/.dsh/ 即视为已安装）。宿主版本探测、文档查询和新会话黑盒测试不是默认步骤；仅在实际路径行为与本契约矛盾或用户明确要求时执行。

单次自动收敛

1. 快速盘点

先检查根入口的类型和 readlink -f 终点，不展开完整 skills 列表：

范围	Prompt 入口	Skills 入口
user	`~/.codex/AGENTS.md`、`~/.codebuddy/CODEBUDDY.md`、`~/.claude/CLAUDE.md`、`~/.kiro/steering/*.md`、`~/.gemini/config/AGENTS.md`、`~/.pi/agent/AGENTS.md`、`~/.config/devin/AGENTS.md`、`~/.config/amp/AGENTS.md`	`~/.codex/skills`、`~/.codebuddy/skills`、`~/.claude/skills`、`~/.kiro/skills`、`~/.gemini/config/skills`、`~/.config/devin/skills`
project	`AGENTS.md`、`CLAUDE.md`、`.kiro/steering/agents.md`；CodeBuddy 无 `CODEBUDDY.md` 时直接使用 `AGENTS.md`	`.agents/skills` 及需要专有入口的宿主项目 skills 目录

Read the full file on GitHub · 138 lines

Files

What ships with it

3 files 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.

19d ago Changed · +2 lines 380fe18edb00
1mo ago Changed · +3 lines 31a79b941986
1mo ago Changed 79d6a0e6edd6
1mo ago Changed · +5 lines ccd1953b8c18
2mo ago Changed · +18 lines fb5c8762a9a2
2mo ago First seen · 110 lines · 44 tokens per session scan B 7c5c42591878

Subscribe to this mod's changes

harness-config-sync is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 4,563 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

Building agents Productivity

harness-config-sync next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-config-synchxy91819/mason-skills	Skill	3	today	MIT	B	44	Claude Code, Codex
orbit-notionnexu-io/open-design	Skill	107k	today	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	112k	today	MIT	A	30	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	2d ago	MIT	A	184	Claude Code
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	today	MIT	A	33	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	11d ago	MIT	A	52	Claude Code, Codex

harness-config-sync