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 commands/n9e/fe/n9e-config-driven-e2egit clone --depth 1 https://github.com/n9e/feWhat 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 | $0.00043 | $0.02102 |
| Opus 5 | $0.00022 | $0.01051 |
| Sonnet 5 | $0.00009 | $0.00420 |
| Haiku 4.5 | $0.00004 | $0.00210 |
Grade A, and why
n9e-config-driven-e2e 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 today.
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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n9e Config-Driven E2E
Use this skill when working on Nightingale config-driven E2E flows. This includes alert-rule creation under e2e/add-alert-rule, and should also guide future flows that start from structured JSON config data. The general pattern is:
JSON 配置数据 -> normalizer 转换为 UI 可读/可操作值 -> Playwright + Midscene 执行页面操作 -> API 回查验证保存结果
This skill is no longer only about adding one alert-rule JSON file. Treat it as the standard way to build E2E coverage for product forms whose source of truth is an exported/API JSON config.
Architecture
- Config files live under a feature-specific
configs/directory, currentlye2e/add-alert-rule/configs/*.json. config-loader.tsdiscovers config files and supportsE2E_CONFIGS=<stem>filtering.reference-data.tsresolves ID-backed fields into visible UI labels.normalizer.tsconverts API/export JSON into a UI-readable normalized model and builds the expected persisted payload.- Step files under
steps/fill page cards or sections from the normalized model. - Datasource-specific query/condition behavior lives under
queries/. - The main test file orchestrates: load config, fetch references, normalize, fill steps, save, API 回查, subset assert, cleanup.
Core Principle
Never silently skip a non-default config field.
If JSON contains a meaningful field, do one of these:
- Fill it into the UI through the correct step handler.
- Normalize it into the exact visible UI value first, then fill it.
- Document a real FormNG/API transformation in
buildExpectedAlertRule(). - Fail with a precise TODO only when no UI path exists yet.
Do not delete expected fields merely to make assertions pass.
Source-Code First
Before changing E2E logic, inspect the product code that owns the form:
- Start with
src/pages/alertRules/FormNG/index.tsx. - For API/export config shape vs page form shape, inspect
src/pages/alertRules/Form/utils.ts.processInitialValues()shows how API/export data becomes FormNG form values.processFormValues()shows how FormNG values become save payload.
- For step-card UI:
- Basic/datasource/rule:
FormNG/index.tsx,FormNG/Rule/**, datasource plugins. - Query/trigger:
FormNG/Rule/**,FormNG/components/Triggers/**. - Event handling:
FormNG/PipelineConfigsNG/**. - Effective config:
FormNG/Effective/index.tsx. - Notify config:
FormNG/Notify/**.
- Basic/datasource/rule:
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.
- today First seen · 180 lines · 43 tokens per session scan A 811e5e6514cb
n9e-config-driven-e2e is a command published in the GitHub repository n9e/fe (302 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 2,102 once invoked, about $0.0002 per session on Opus 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 2026-09-01.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.