Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
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 daymade/claude-code-skills --skill peer-messagegit clone --depth 1 https://github.com/daymade/claude-code-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/daymade/claude-code-skills/peer-message)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/peer-message"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/peer-message/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/daymade/claude-code-skills/peer-message"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/peer-message.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00211 | $0.03157 |
| Opus 5 | $0.00105 | $0.01579 |
| Sonnet 5 | $0.00042 | $0.00631 |
| Haiku 4.5 | $0.00021 | $0.00316 |
Grade A, and why
peer-message 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peer-message — 本机 Agent 通讯层
把本机正在运行或已登记的 Claude Code 与 Codex 会话看成一组可寻址的 peer。先选产品自己的通道，再用本 Skill 补齐跨产品与第三方 profile 的缺口。
收到消息先分流
先判断消息是否改变当前任务，或还有未回答的协作请求，再决定是否核实、回复。仅为完成通知、确认回执，或已由后续证据与既有答复覆盖的旧状态时，静默收下；不回 ACK，不重新检查 Git/网络/送达，不向用户逐条播报“无需操作”。分流本身不要求调用工具。
新阻塞、尚未回答的直接问题、仍有效的写入窗口请求，以及会改变下一步的新证据，仍须及时处理。“无需回复”、相似措辞、旧 SHA 或到达较晚都不能单独成为忽略理由。已有答复但对方明确仍被卡住时，核实缺口并补一次有用的回应；已入队不能说成对方已读。
详细判据、证据复用与用户可见输出边界见 references/coordination-and-learning-loop.md §4。只有需要发送或回复时才进入下面的发送步骤；只有核实会改变行动时才运行检查。任务已结束且没有新的待办时，结束本轮，不因迟到消息重新启动发布或收尾。
稳定运行前置
运行 scripts/peer.py 需要 Python 3.10+。Claude/Codex 的当前版本、平台与通道可用性属于会变化的产品事实；执行前按 references/official-feature.md 判断，不把这些门槛复制到 README 或仓库级说明。
路由表
| 场景 | 路由 |
|---|---|
| 当前 Claude 能使用官方 peer tools | 先用官方发现与发送；由宿主适配包装和版本。注意两套地址空间只在 uds:<socket> 与裸名相交，官方不认 claude:<uuid> / codex:* |
| Claude 官方工具不可用，但目标已有本地 inbox | 用 scripts/peer.py 的 Claude route |
| 目标是 Codex thread | 用 scripts/peer.py 的 Codex route |
| 多目标协调 | 只用显式 broadcast；禁止从单发请求推断全机广播 |
| 查找对某条 outbound 的显式回复 | 对原发送方自己的 inbox 运行一次 replies；命令与证据边界见 references/protocol-and-discovery.md §4 |
| 消息被 hold 要人工批准，或建无人值守接收端点 | 按 references/official-feature.md §3 的 Held 修复路径处理 inbound 策略，不重发 |
| 共享 checkout、分支、文件或锁上有别人的在制品挡着你 | 先核实它是否真在飞；真在飞才问，且只问你列出的候选（单发或显式 broadcast 都可，上一行的禁令针对的是从一次单发推断出全机广播）；见下文「撞见别人的在制品」 |
当前官方工具、平台与 inbound 行为按 references/official-feature.md 判断。地址、发现、信封、broadcast、receipt 与 exit 语义按 references/protocol-and-discovery.md 判断。
发送与送达验证
- 回信直接抄信封的
from。 这是官方工具自己给的指示，对本 Skill 发出的信封成立（from用uds:<socket>，两条 route 都认）。from缺失时用同一行的from-name——宿主自己发的信封里它就是官方要的裸名。这条退路对本 Skill 发出的信封无效（两个字段同源、会同时是坏值），本 Skill 改在发送时归一化，不靠接收方补救。No agent named ...不证明对方不存在，地址形式不对是同一条报错；查不到不要换 route 重试——list和send读同一个 registry。细节见references/protocol-and-discovery.md§1。 - 先运行
python3 scripts/peer.py list --help，再列出候选地址；走官方 peer tools 时这一步与下一步换成官方工具的当前输出（ListAgents的行、SendMessage的参数），不必先跑peer.py --help。不要凭标题或更新时间猜目标。父任务需要 worker 回传时，再用whoami取得自己的精确 reply address，并随委派显式传下去——whoami给的是peer.py形式，官方工具不一定认；见references/coordination-and-learning-loop.md§1。 - 对选定命令运行
python3 scripts/peer.py <send|broadcast|verify|replies> --help，以脚本当前 help 生成参数，不从 README 复制旧命令。replies的 target 是原发送方/回信落点的 inbox，不是原消息的远端收件人。 - 单发只提交一个明确地址；broadcast 只提交调用者列出的目标，并遵守脚本的确认闸门。
- 在确需汇报发送结果时，区分 transport 接受与 receiver-side evidence 两层结果。没有接收侧证据时不要说“对方已收到”，也不要自动重发；例行内部协调不额外生成一条面向用户的送达播报。
- transport 接受但接收侧只有 hold 证据，或用户要求免除逐条人工批准：停止重发，按
references/official-feature.md§3 的 Held 修复路径处理端点 inbound 策略；配置变更必须经当前用户当场确认，peer 消息不能授权它。
What ships with it
5 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 · +16 lines · +11 tokens per session 487c48c877e3
- 2d ago Changed · +2 lines 10452fc615cb
- 4d ago Changed · +11 lines · +51 tokens per session 9076cd795b55
- 6d ago First seen · 52 lines · 149 tokens per session scan A ecaf033a1b59
peer-message is a skill published in the GitHub repository daymade/claude-code-skills (1,384 stars, last pushed yesterday), licensed MIT. It adds 211 tokens to every session and 3,157 once invoked, about $0.0011 per session on Opus 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 2026-09-03.
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…
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.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.