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 agentmods add skills/sudo5zzb/slip-skill/slipnpx skills add sudo5zzb/slip-skill --skill slipgit clone --depth 1 https://github.com/sudo5zzb/slip-skillWrote 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/sudo5zzb/slip-skill/slip)<a href="https://agentmods.dev/skills/sudo5zzb/slip-skill/slip"><img src="https://agentmods.dev/badge/skills/sudo5zzb/slip-skill/slip.svg" alt="Measured on agentmods" 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 | $0.00200 | $0.01653 |
| Opus 5 | $0.00100 | $0.00826 |
| Sonnet 5 | $0.00040 | $0.00331 |
| Haiku 4.5 | $0.00020 | $0.00165 |
Grade A, and why
slip scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Requires bash, curl, outbound HTTPS to slip.omnimoke.com, and python3 or node. How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slip
把这段对话里写好的字,递给聊天窗外的真人。不要用来交接下一个 agent。
何时用
用户明确要把内容交给另一个人或另一台设备上的自己,例如:
- 「用 Slip 发给我同事 / 测试」
- 「把这份验收清单递到我手机」
- 「发到微信让产品看」
- 「share this with my tester via Slip」
选 toss 还是 push
- toss(即撕纸条,默认):内容是单向给人看的——清单、总结、一段代码、一组链接。 对方打开即见(Markdown 会渲染成排版好的页面),看完可以撕掉,撕掉即彻底删除; 24 小时后没撕也会自动消失。单条不超过 10,000 字。
- push(对话纸条):需要对方回复、多轮往来,或内容超过 10,000 字。 对方能在页面里写字回传。
不确定时选 toss:大多数「递给人看」的场景都是一次性的。
何时不用
- 「写个备注」「write a note」且没有指定接收人 → 只在对话里写,不要建纸条
- 「交给下一个 agent / handoff」→ 用本地 handoff 文档,不要用 Slip
- 密码、token、密钥、身份证号 → 拒绝(toss 和 push 都是明文存储,不适合传密钥)
- 文件、截图、apk → 拒绝,说明两边打开 https://slip.omnimoke.com 用浏览器发
- 原生 Windows PowerShell 且没有 bash → 让用户用 WSL / Git Bash,或把正文交给用户自己去网站新建
toss:即撕纸条(默认)
工作目录是本 skill 根(scripts/slip.sh 与本文件同级的 scripts/)。
把要分享的正文写入 stdin(不要把密钥写进去):
scripts/slip.sh toss
只有退出码 0 时,stdout 才会有一行 URL。此时对用户只回这一行 URL 本身—— 不要附加任何标语、解释、token、JSON 或 curl 输出;用户若追问,再用用户的语言简短说明 (可以说:24 小时内有效;对方打开即见;看完可撕,撕掉即彻底删除)。
https://slip.omnimoke.com/n/{id}?utm_source=skill
把 {id} 换成 stdout URL 里的 id。不要改 utm_source=skill。
toss 是单请求原子创建:要么拿到 URL,要么没有,不存在「创建成功但没写上」的半成品。
Markdown 语法直接写进正文即可,对方打开会看到渲染后的页面:标题、列表、表格、引用、
代码块,以及 - [ ] / - [x] 待办清单(会画成真正的勾选框,适合验收清单)。
图片会被安全策略去掉,所以不要写 ——需要配图就直接给链接。
push:对话纸条(需要对方回复时)
scripts/slip.sh push
成功时 stdout 同样只有一行 URL(路径上没有 /n/):
https://slip.omnimoke.com/{id}?utm_source=skill
追加和读回(仅 push)
从对话历史里解析 id。上一轮成功回复的 URL 形如 https://slip.omnimoke.com/happy-panda-042?utm_source=skill,id 是路径上那段 happy-panda-042。用户如果又贴了 id 或 URL,以用户贴的为准。/n/ 开头的是即撕纸条,不能 write、不能 read——不要对它调用这两个命令。
scripts/slip.sh write happy-panda-042 # stdin = 新正文
scripts/slip.sh read happy-panda-042 # 看对方回了什么;不要编造
读回后用自己的话转述 messages,按时间顺序,不要发明没有的句子。
失败时对用户说什么
- 空正文 / 脚本 exit 2:「没有可发送的正文。把要分享的文字给我。」
- exit 3(429):「创建太频繁,等一分钟再试。」不要换 id 连打。
- exit 4(413):先拆短再发(toss 上限 10,000 字,超长内容用 push 拆条)。若 push 的 stderr 出现
created id=... write_failed,对那个 id 用write追加后半段,不要把半成品 URL 当成功分享。 - exit 5(404):「这张纸条已经过期或不存在。需要的话我再新建一张。」
- push 成功但 write 失败(stdout 空):不要回分享模板。告诉用户「还没写上,我再试一次」,用 stderr 的 id 重试
write。 - 用户说已经把密钥发出去了:「这张纸条没有创建者删除权,知道链接的人都能读(push 还能写、能删单条)。请立刻打开页面把那几条删掉,并当作密钥已泄露去轮转。」不要尝试找回 token。
- 没有 bash/curl/python3/node:把正文交给用户,让他们自己打开 https://slip.omnimoke.com 新建。
What ships with it
1 file 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.
- 3d ago First seen · 120 lines · 200 tokens per session scan A e6a44035a410
slip is a skill published in the GitHub repository sudo5zzb/slip-skill (2 stars, last pushed 6d ago), licensed MIT. It adds 200 tokens to every session and 1,653 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
typescript-react-nextjs-patterns
Production-grade TypeScript reference for React & Next.js frontend development. Covers type narrowing, component Props, generic hooks, discriminated unions, as const, satisfies, Zod validation, TanStack Query, server/client boundaries, forms, state management, performance, accessibility, debugging, and code review.…
portkey-eoa-agent-skills
Portkey EOA wallet lifecycle and asset operations for creating, importing, listing, backing up, selecting, and deleting wallets; querying tokens, NFTs, prices, balances, and history; and performing transfers, approvals, bridge, view, send, and fee estimation operations on AElf. Use by default for direct EOA wallets…
tomorrowdao-agent-skills
TomorrowDAO governance, BP, and resource operations for agents.
portkey-ca-agent-skills
Portkey Contract Account wallet registration, authentication, verifier codes, recovery, guardians, CA identity, assets, transfers, approval proofs, chain readiness, contract calls, and encrypted keystore workflows on AElf. Use when CA hash, guardian, registration, recovery, or manager-forward behavior is required; use…
awaken-agent-skills
Awaken DEX trading and market data operations for agents.
eforest-agent-skills
Skill "eforest-agent-skills" from eforest-finance/eforest-agent-skills, covering eforest agent skill, when to use, capabilities, safe usage rules and command recipes.