Security intelligence for the agent supply chain

猫眼电影个性化推荐系统——每周抓取中国大陆新上映/即将上映电影，基于用户观影偏好档案智能排序推荐，推送飞书周报

Access HL Privateer, an open agentic Hyperliquid discretionary trading desk. Read live positions, AI analysis, copy-trade signals, and risk state via x402 pa...

Ship code with oneshot CLI. One command that plans, executes, reviews, and opens a PR. Runs over SSH or locally. Use when the user wants to ship code changes...

Cash out Base USDC to fiat through Peer with custody-separated MCP tools.

Invisibly classify work and choose Codex or Claude, reasoning effort, context shape, execution style, and verification profile. Use before agent, oneshot, Sl...

Send SMS jobs and check SMS delivery status through the Retarus SMS for Applications REST API. Use when Codex or OpenClaw needs to create SMS jobs, inspect p...

Podcast discovery for Wherever.Audio -- find shows and episodes, generate wherever.audio links.

Set or update environment secrets via the set-secret GitHub Actions workflow. Use when the user asks to update, rotate, or set a secret/token/API key for thi...

Publish, create, and update Confluence pages from HTML content.

Am I going in circles? Am I repeating myself? Use this when something feels familiar, when progress stalls, when the same command or URL comes up again, or every ten tool calls on a long task. Measures repetition in this session's recent to

Am I using too many tokens? Am I spending tokens to refute myself instead of executing? Am I overthinking? Use this every ten turns on a long task, when a good first idea seems to be drifting, when several text-only turns have passed withou

How do I breed two agents into a better one? Can two OpenClaw agents have offspring? Use this when you have two agents that each work and want a third that inherits from both: it crosses their workspace genome (AGENTS.md, SOUL.md, TOOLS.md,

ClawPhylax: did that actually work? Did my message actually go out? Is this safe to send? Why did my request fail? Should I stop and ask? Am I going in circles? What did I lose in compaction? What did I actually do? The full list of the 22

Is this skill safe? Use this before installing any third-party ClawHub skill or running its scripts, and whenever the user asks whether a skill is safe. Inspects every file in the skill folder — SKILL.md and scripts — and reports every netw

Could this get the user banned, charged, or exposed? Use this before any action against a third-party service — a request to a host that has refused or rate-limited you, a curl/wget/requests upload, an exec that reads ~/.ssh, .env or ~/.aws

Did I do what was asked? Does my reply match the request, and did the processing in between make sense? Use this after replying to a message, before marking a task handled, when a heartbeat or cron turn produced many tool calls for a small

Did my message actually go out? Was it delivered, or did the send only look successful? Use this after any message send whose delivery matters — a notification, a reply the user is waiting for, a forward to another chat — and before telling

Did that actually work? Did my last action take effect, or did it only look like it did? Use this after any tool call whose effect matters — an exec, a write, a POST or PUT, a message send, a fetch you will build on — and before reporting s

Do I know enough to act? Am I acting blind, or exploring forever? Use this before the first irreversible action (write, exec that changes state, message, purchase) and when several writes or commands have failed in a row. Compares gathering

Has another agent or session on this machine already solved this? Has this host already been reached? Use this before a costly or hard fetch, when working alongside another agent, when a host is hard to reach, or before re-fetching somethin

Is this safe to send? Am I sending this to the right chat, and does it contain anything that must not leave? Use this before sending a message to any target other than the conversation you are replying in, before forwarding content between

Should I stop and ask the user? Is this task possible with what I have? Use this when a task is failing repeatedly, the same approach has been tried twice, no new evidence is appearing, a host is refusing you, or you are about to ask a vagu

Where does this skill send data? What hosts did it contact? Use this when the user asks what an installed skill is doing on the network, why the agent contacted an unknown host, after a ClawPhylax footer flags a host, or before trusting a s

What do I believe I did, and what did I actually do? Did the things I told the user really happen? Use this before reporting a task as done, after a long session, and whenever you are about to say 'sent', 'published', 'fixed', 'installed' o

What did I lose in context compaction that I must not forget? What happened before my context was cut? Use this right after a compaction notice, at the start of a resumed session, when an earlier result seems missing from your context, and

What has this task cost so far? Why is my OpenClaw bill so high? How many tokens has the agent used? Use this before deciding whether another attempt is worth it, when the user asks about cost or tokens, when a task has run for a long time,

What worked here, and how do I do it again? Which tool and route succeeded on this host, and is it repeatable? Use this after finally succeeding on a difficult host, when asked to make a result repeatable, or before writing a workspace skil

Which path is worth it? Which research or action path should I try next under incomplete information? Use this when choosing between two or more approaches, planning research, deciding where to spend a limited budget, or when the user asks

Why did my request fail? Should I retry, wait, or switch tools? Use this before retrying a failed web_fetch, API call, browser request or network exec — especially after a timeout, 401, 403, 429 or 5xx, or after two unsuccessful attempts. D

Why do I keep failing? What is the pattern behind my errors? Use this when errors pile up — three or more failed tool calls (exec, write, web_fetch, API) in a session — before retrying anything. Clusters this session's failed tool calls and

Lybic Sandbox is a cloud sandbox built for agents and automation workflows. Think of it as a disposable cloud computer you can spin up on demand. Agents can perform GUI actions like seeing the screen, clicking, typing, and handling pop ups,

Explore an agent community and persistent agent-to-agent conversations on AgentCollabSpace. Read public invitations without an account; join discussions, share ideas, or resume a saved identity when participation is authorized. Use for agen

Enforcement and accountability layer for AI agents. Bring your own identity (did:key, did:web, SPIFFE, OAuth, did:aps). Gateway enforcement boundary, monotonic narrowing, cascade revocation, spending controls, data lifecycle, observation go

The base layer an AI agent runs on to be verifiable, accountable, and able to work with the world. One slug adds a controlled Ed25519 identity tied to the principal behind the agent, scoped authority that only narrows, a signed receipt for

Find people through your agent. Tell your agent who you're looking for and Mingle helps find the right person through their agent.

Early release. The AEOESS skill for agents that operate accountably: verifiable Ed25519 identity tied to the principal, scoped authority that only narrows, a...

EvoMap AI Agent 协作进化市场工具箱。用于发布、获取和管理 Capsule，参与任务赚取积分。

按需记忆检索。当用户询问历史相关问题时，自动搜索 memory 和 QMD 获取相关信息。

管理待办事项。添加、查看、完成、删除待办。

中文长篇小说单书工作流：章节 preflight、连续性记忆、写作原则、质量门和 Markdown 交付

The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.

Get your own home on the internet - a profile page with a public inbox at home.ctxly.app

Cloud memory for AI agents. Store, search, and recall context across sessions.

Anonymous private chat rooms for AI agents. No registration, no identity required.

Proactive Chinese language tutor that delivers curated, real-world Mandarin learning content on a schedule. Use when: (1) User wants to learn or improve Chin...

Proactive Chinese language tutor that delivers curated, real-world Mandarin learning content on a schedule. Use when: (1) User wants to learn or improve Chin...

Tap into 2,500-year-old Daoist wisdom from the Dao De Jing (道德经). When facing a modern decision, stress, or mental block — ask The Way. It matches your conce...

Tap into 2,500-year-old Daoist wisdom from the Dao De Jing (道德经), fused with modern cognitive reframing. When facing a modern decision, stress, or mental blo...

将任意舆情事件按Duncan五阶段方法论（发生→爆发→高潮→缓和→降温→反馈）进行结构化分析，输出标准化报告。适用于政企危机、品牌公关、政策舆情等场景。

Claw Compactor v6.0 — 50%+ savings through rule-based compression, dictionary encoding, session observation compression, and progressive context loading.