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.
npx skills add hxy91819/mason-skills --skill harness-config-syncgit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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.
[](https://agentmods.dev/skills/hxy91819/mason-skills/harness-config-sync)<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.
<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>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 | $0.03829 |
| Opus 5 | $0.00022 | $0.01914 |
| Sonnet 5 | $0.00009 | $0.00766 |
| Haiku 4.5 | $0.00004 | $0.00383 |
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 today.
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。 How it starts
The opening of the file, as written. The whole thing — 133 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。 - 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）和 Devin（存在 devin 可执行文件或 ~/.config/devin/ 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 |
~/.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 |
Kimi Code 走原生快速路径：user scope 直接检查 ~/.agents/AGENTS.md、~/.agents/skills/，project scope 直接检查从项目根到当前目录适用的 AGENTS.md/agents.md 和 .agents/skills/。仅当已有 Kimi 专有内容时再检查 $KIMI_CODE_HOME/AGENTS.md、$KIMI_CODE_HOME/skills/、项目 .kimi-code/AGENTS.md 与 .kimi-code/skills/；KIMI_CODE_HOME 未设置时默认为 ~/.kimi-code。
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.
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.
- today Changed · +5 lines ccd1953b8c18
- 6d ago Changed · +18 lines fb5c8762a9a2
- 8d ago First seen · 110 lines · 44 tokens per session scan B 7c5c42591878
harness-config-sync is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 3,829 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.