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-preflightgit 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-preflight)<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/release-preflight"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-preflight/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-preflight"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/release-preflight.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 | $0.00076 | $0.04086 |
| Opus 5.5 | $0.00030 | $0.01634 |
| Sonnet 5.5 | $0.00015 | $0.00817 |
| Haiku 4.5 | $0.00008 | $0.00409 |
Grade A, and why
release-preflight 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release-preflight
发版最前面的只读硬前置门(apc/01 §2 release-preflight,收口步 1/2/5)。它跑三道检查——tier 门(真跑 run.ts,读真退出码)、版本对齐(/VERSION ⇄ 承载文件)、prisma regen(源 schema ⇄ generated client 逐字节)——收敛成一个 decision。全程只读 / 本地,不 push、不写库、不发版。
什么时候用:任何 release-tag / ota-promote 之前的第一步。没跑过 preflight 拿到 green 就去 tag,是在拿没验过的栈发版。
承重纪律(发版 skill 的命根子,先记死)
--tier必须显式传,没有默认值。TD(桌面冒烟)在apps/desktop/e2e/smoke/无真跑 spec(RUN_ELECTRON_SMOKE!=1时自动exit 77skip)时会占位passed:0/failed:0——单独拿它当发版硬前置是一道不可能红的空门(apc/12§0.12:之前 SKILL 范例全不带--tier让 agent 照抄默认值正是这么踩的坑)。选一个会真执行断言的层,例如--tier=T0,T1。- tier 绿是发版的硬前置,"绿"必须是真跑过用例。tier 红 /
env_blocked/ 空跑(该轮所有 tier 的passed+failed合计为 0,一个用例都没真执行,即便exitCode是 0)⇒blocked——发版根本不该起步,preflight 直接拦在这里。别把 tier 红当成"发版流程的问题"绕过去:那是被测栈的红,先修栈;也别挑一个恰好全 skip 的层去骗过门。 - preflight 只诊断,不修。版本失配 / prisma 待重生是
staged(可修前置),它给你 fix-hint(sdk/build/version.sh/npm run prisma:generate:all),由你或人去修,preflight 不代跑。 - 这是只读门:它不碰 prod、不碰远端、不 push。prod 红线由
release-tag/ota-promote的人闸把守,preflight 不涉及。
Anti-pattern(这些做法直接判红)
- ❌ preflight
staged就当 green 往下发版。staged(exit 3)不是 green(exit 0)——有未对齐的版本 / 未重生的 client,带病发版。 - ❌ preflight
blocked(tier 红)时放松 tier 或改--tier挑一个能绿的层去骗过门。tier 门跑的是真run.ts,红就是栈红。 - ❌ 不看退出码只看输出文本。
decision+ exit code 是承重信息;"看起来没问题"不是证据。
工具契约(签名以此为准)
apc不在 PATH——在仓库根一律用npx tsx sdk/apc/bin/apc.ts <sub>跑(stdout 是纯 JSON)。
| 命令 | 作用 | 退出码 |
|---|---|---|
npx tsx sdk/apc/bin/apc.ts release preflight --tier=<tiers> [--json] |
tier 门 + 版本对齐 + prisma regen 三道只读检查 | 0 green · 3 staged · 1 blocked(tier 红 / 空跑 / env_blocked)· 2 用法错(缺 --tier) |
--tier 没有默认值,不传直接 usage 错 exit 2。选一个会真执行断言的层,例如 --tier=T0,T1——别用 --tier=TD 当唯一层:无桌面冒烟 spec 时它是空门。
--json 出结构化回执(审批人证据包)。字段(名以此为准):
- 顶层:
{ verb:'preflight', decision:'green'|'staged'|'blocked', tier, version, prisma, blockers:[], staged:[] } tier:{ tier, exitCode, envBlocked, regressions:[], emptyRun }(exitCode是 run.ts 真退出码:0 绿 / 1 SUT 红 / 78 env_blocked;emptyRun:true= 该轮所有 tier 的passed+failed合计为 0,一个用例都没真跑,即便exitCode:0也判blocked)version:{ aligned, rootVersion, mismatches:[{file,found}] }prisma:{ ok, stale:[{schema,reason}] }
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 · 175 lines · 76 tokens per session scan A 7b8026198136
release-preflight is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,384 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 4,086 once invoked, about $0.0003 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
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
CI Pipeline Optimizer
Optimize CI test pipelines through intelligent test splitting, parallelization, caching strategies, and selective test execution based on code changes.
Flaky Test Quarantine
Detect, quarantine, and systematically fix flaky tests with automated retry analysis, root cause categorization, and CI pipeline integration for test reliability.
Checkly Monitoring as Code
Teach agents to build synthetic monitoring as code with Checkly, including Playwright browser checks, API checks, alerting, and CI deploy workflows.
CI Test Sharding Parallelization
Teach agents to shard and parallelize Playwright, Jest, and pytest suites in CI to reduce wall-clock time while merging reports reliably.
Advanced Chaos Engineering
Advanced chaos engineering patterns using Chaos Monkey, Litmus, and Gremlin for testing distributed system resilience under failure conditions.