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 test-result-feedbackgit 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/test-result-feedback)<a href="https://agentmods.dev/skills/prismer-ai/prismercloud/test-result-feedback"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/test-result-feedback/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/test-result-feedback"><img src="https://agentmods.dev/badge/skills/prismer-ai/prismercloud/test-result-feedback.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 | $0.00065 | $0.05040 |
| Opus 5.5 | $0.00026 | $0.02016 |
| Sonnet 5.5 | $0.00013 | $0.01008 |
| Haiku 4.5 | $0.00006 | $0.00504 |
Grade A, and why
test-result-feedback 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 17d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-result-feedback
把 apc test 的 TierResult 回流成 task 每条验收 criterion 的 结构化判定 + 证据（apc/05 C2 · S5b）。这是「测试→回流」的后半段：test-runner 负责选层跑并把新增红报回一条 criterion；本 skill 负责把一轮 TierResult 摊到 task 的每一条 criterion 上，逐条 passed/failed/n/a 落库并挂证据 ref，喂给循环级视图（cockpit 用 task metadata loopId 聚合，不建 loop 实体）。
承重纪律（本 skill 存在的唯一理由）：红是一个发现，不是要修绿的对象。 TierResult 里一条 SUT 红 → 对应 criterion 必须报 failed 并附失败证据；绝不因为"就差一点"或"看起来还行"把红判成 passed。把断言放松到红能过 = 作废（CLAUDE.md 验收纪律 §3）。判定只取自 TierResult 的结构字段（exitCode/failedNames/regressions[]/pass 计数），绝不取自 agent 自己的聊天叙述——文本会冒充证据。
什么时候用：一个 coding task 跑完测试（test-runner 产出或 apc test --json），需要把这轮结果逐 criterion 落回 task 的验收账、并留下可回读的证据 ref。
工具契约（签名以此为准，先核后用）
| 命令 | 作用 | 退出码 |
|---|---|---|
apc test [--tier=T0,T1] [--diff] [--json] |
全层测试编排（包装 scripts/test203/run.ts），产出 TierResult |
0 绿 · 1 SUT 红/回归 · 2 用法错 · 78 env_blocked |
cloud task verify-criterion <task-id> <criterion-id> --outcome <passed|failed|n/a|waived> [--evidence <ref>...] [--note <md>] |
把一条 criterion 的判定 + 证据报回 task | 0 成功 |
cloud task acceptance <task-id> |
读回 acceptance-view（回读确认 criterion 落库） | 0 成功 |
--outcome合法值恰好四个：passed/failed/n/a/waived（其它值 CLI 直接报错）。--evidence <ref>可重复，取值形如taskRun:<runId>/asset:<id>/url:...——把这轮 TierResult 的可追溯锚挂上去（典型：把apc test --json产物cloud asset upload成 asset 后引asset:<id>，或引 dispatch 的taskRun:<id>）。报failed必须带证据，否则就是空口判红。--note是自由 markdown：写清判定方法 + 失败用例名（failedNames）+ 复现指令。
TierResult 字段（以 FIELD-DICTIONARY.md 为准，别照抽象词猜）
apc test --json stdout 顶层：{ schema, doctor, envStatus, tiers:[...], regressions:[...], fixed:[...], exitCode }。
exitCode：整轮退出码（0绿 /1SUT 红（--diff下=新增红）/78env_blocked）。regressions[]：新增红 vs baseline（跨所有层并集）——判"回归"只看它，baseline 已知红不算本轮的红。- 每个
tiers[]（TierResult）：{ tier, passed, failed, skipped, total, failedNames:[...], skippedNames, regressions, envStatus, durationMs }（是failedNames驼峰；command/exitCode在顶层不在每层）。
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.
- 17d ago First seen · 240 lines · 65 tokens per session scan A 91f6b8e8a545
test-result-feedback is a skill published in the GitHub repository Prismer-AI/PrismerCloud (1,386 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 5,040 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
testgen-flow
Workflow for generating test cases from requirements (Issue Tracker / Wiki sources), exporting to a Test Management System, etc.
lov-atom-feature-dev
An end-to-end workflow for building a small, self-contained feature across its shared core, command-line tool, API, user interface, saved parameter presets, agent tool, and debugging panel. It uses one contract and shared test cases across the pieces.
lov-atom-operations
A checklist and implementation workflow for making a completed feature ready to explain, test, find, authorize, sell, measure, and maintain. It decides which supporting work applies instead of adding every integration by default.
nightly-close-parity
Unique project-local fire verb for the seven-leg nightly close-parity pass. Proves and loads the canonical top-level skill.
gsd-validate-phase
Retroactively audit and fill Nyquist validation gaps for a completed phase.
test-plan
Build a test plan when a new Epic is created. Pulls epic details and linked stories from Jira, analyzes scope, and produces a test plan covering strategy, automation gap analysis, success criteria, environment needs, and risks. Output goes to Confluence and local test knowledge base. Use when: "test plan", "plan tests…