Prismer Cloud is an infrastructure layer for AI agents that provides shared learning, compressed context, persistent memory, collaboration, messaging, tasks, identity, and workspaces. It is for agents and the people building or using long-running agent systems that need information and outcomes to persist across sessions. The catalogue entries provide skills, hooks, agents, instructions, and a plugin for using Prismer Cloud.
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 Prismer-AI/PrismerCloud --skill release-ota-promotegit clone --depth 1 https://github.com/Prismer-AI/PrismerCloudWrote 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/prismer-ai/prismercloud/release-ota-promote)<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/release-ota-promote"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-ota-promote/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/prismer-ai/prismercloud/release-ota-promote"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-ota-promote.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 | $0.00052 | $0.04138 |
| Opus 5.5 | $0.00021 | $0.01655 |
| Sonnet 5.5 | $0.00010 | $0.00828 |
| Haiku 4.5 | $0.00005 | $0.00414 |
Grade A, and why
release-ota-promote 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 18d 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.
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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release-ota-promote
把一份 runtime OTA 沿双通道下发（apc/01 §2 ota-promote，收口步 7/8/11）。这是线 3 admin fleet 下发，交付模式治 doc01 #8（"promote 用了线 1 kill1 而非线 3 drain_respawn"）：
- K8s daemon 通道：交付 drain_respawn（排空在飞 task → 优雅
exit(0)→ supervisor respawn → boot-OTA 换版，用户无感/无中断）。正规落点 = admin fleet rollout endpointPOST /api/admin/runtime-releases/rollout（src/im/api/admin.ts）→ 给每个目标 daemon 下发runtime.update.apply帧 → daemon arm drain_respawn。本 verb 不再 spawn 线 1kill 1的runtime-ota.ts（那会打断在飞 task），而是构造这条 drain_respawn rollout 请求。本机替身只 dry-run 出请求、不真 POST（真 POST 需 approvalId + release row + 在线 daemon = M5）。 - 桌面 feed 通道：本机替身未接线——诚实标 ⬜（铁律 4）。缺①桌面本地 feed 基座（
apc/05§3，P0-4 未落）②本机禁写真 Nacos manifest（= M5）。
什么时候用：一个新 runtime 版本发布后，要让 fleet 里的 daemon 采用它。
承重纪律（发版 skill 的命根子，先记死）
- prod OTA 必拒（不变量 2）。
--env prod先于任何 OTA 动作硬拒，不做任何下发。别试 prod：真 prod promote = M5。 - 交付模式 =
drain_respawn，绝非kill1。线 3 fleet 下发必须排空在飞后再 respawn（kill 1会打断用户在飞 task，那是线 1，仅 dev/紧急）。k8s.directive必须是drain_respawn。 - 不宣称
drain_respawn已执行。本机替身只 dry-run 出 rollout 请求（k8s.posted:false），不真 POST（= M5：approvalId + release row + 在线 daemon）。照实报"已构造 drain_respawn 请求，未真下发"，绝不说"已 drain_respawn 下发"。 - 桌面 feed 走真文件副作用。传
--desktop-feed-dir与 UI/daemon builder metadata；verb 先校验 size + SHA-512，复制版本化 bundle，最后原子切manifest.json，再从磁盘回读摘要。只有desktop.status:'applied'+readback.verified:true才能宣称 feed 已发布。 - feed 已发布 ≠ Electron 已应用。客户端
check → stage → apply需要另取运行态证据，不得从文件写入外推。
Anti-pattern（直接判红）
- ❌
--env prod想 promote prod。命中即 blocked，别绕。 - ❌ 把交付模式报成
kill1/ 线 1kubectl exec kill 1。本 verb 是线 3，交付drain_respawn；报 kill1 = 把在飞打断当成了正规下发。 - ❌ 把
k8s.posted:false的 dry-run 说成"已 drain_respawn 下发/已 POST"，或把本地 feed 已发布说成"Electron 已更新"。
工具契约（签名以此为准）
apc不在 PATH——在仓库根用npx tsx sdk/apc/bin/apc.ts <sub>。
| 命令 | 作用 | 退出码 |
|---|---|---|
npx tsx sdk/apc/bin/apc.ts release ota-promote [--env dev|test|prod] [--json] |
K8s 通道构造 drain_respawn rollout 请求（落点 admin fleet rollout endpoint，本机替身 dry-run 不 POST）+ 桌面通道 ⬜；prod 硬拒 | 0 green（真 rollout 完成，仅 M5）· 1 blocked（本机 dry-run 边界 / 桌面未接线 / prod 拒） |
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.
- 18d ago First seen · 196 lines · 52 tokens per session scan A d9da60b74c79
release-ota-promote is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,384 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 4,138 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
performing-container-image-hardening
This skill covers hardening container images by minimizing attack surface, removing unnecessary packages, implementing multi-stage builds, configuring non-root users, and applying CIS Docker Benchmark recommendations to produce secure production-ready images.
Docker Compose Generator
Generates production-ready docker-compose.yml files for any application stack.
code-engine-deploy
IBM Code Engine deployment skill. Use when deploying, managing, or troubleshooting IBM Code Engine applications, jobs, secrets, config maps, domain mappings, container builds, or ICR images. Use for: deploy to code engine, code engine app, code engine job, build container image, push image, ICR registry, MCP tools…
Docker Container Testing
Testing Docker containers and images including Dockerfile linting, container structure tests, security scanning, and multi-stage build validation.
docker-management
Manage Docker containers and images via MCP. Use when the user asks to docker ps, tail container logs, restart a service, exec into a container, check CPU/memory stats, or clean up images on the local host.
implementing-container-image-minimal-base-with-distroless
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.