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/packmindhub/packmind/create-run-e2e-testsnpx skills add PackmindHub/packmind --skill create-run-e2e-testsgit clone --depth 1 https://github.com/PackmindHub/packmindWhat 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 | $0.00175 | $0.02695 |
| Opus 5 | $0.00088 | $0.01347 |
| Sonnet 5 | $0.00035 | $0.00539 |
| Haiku 4.5 | $0.00017 | $0.00269 |
Grade A, and why
create-run-e2e-tests 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 2d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring Packmind E2E Tests
Overview
apps/e2e-tests/ runs Playwright against the real frontend (http://localhost:4200) and API. Tests drive the browser through a Page Object Model and seed irrelevant setup data through the API, not the UI. The dev stack must be running first (see michel-run-local-dev-stack).
Two rules dominate everything here, and both come from the project's .packmind standards:
- Never use Playwright's raw
test. Always use one of the project fixtures. They handle user creation, sign-up, and API-key setup so each test starts from a clean, authenticated state. - Drive the UI through Page Objects, never raw selectors in specs. A spec should read like a user story; selectors live inside page objects so a markup change breaks one file, not twenty tests.
Where files go
| File type | Location | Naming |
|---|---|---|
| Spec | src/features/<area>/ |
<Feature>.spec.ts — one spec per feature |
| Page object interface | src/domain/pages/index.ts |
IXxxPage |
| Page object impl | src/infra/pages/ |
XxxPage.ts |
| API gateway type | src/domain/api/IPackmindApi.ts |
Gateway<IXxxUseCase> |
| API gateway impl | src/infra/api/PackmindApi.ts |
— |
| API data factory | src/domain/apiDataFactories/ |
apiXxxFactory.ts |
This mirrors the hexagonal split used across the repo: domain/ holds interfaces, infra/ holds implementations.
Choosing a fixture
The three fixtures form a chain — each extends the previous and adds one capability. Pick the lowest one that gives you what the test needs, so you don't pay for setup you won't use.
| Fixture | Provides | Use when |
|---|---|---|
testWithUserData |
userData (email/password), page |
Testing sign-up / activation / trial itself — i.e. flows that run before a session exists. You drive the PageFactory yourself. |
testWithUserSignedUp |
everything above + dashboardPage (already signed in) |
Testing in-app UI where you don't need to seed API data. |
testWithApi |
everything above + packmindApi |
You must seed standards/packages/skills/etc. before exercising the UI. |
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.
- 2d ago First seen · 191 lines · 175 tokens per session scan A e4880851aeef
create-run-e2e-tests is a skill published in the GitHub repository PackmindHub/packmind (306 stars, last pushed 4d ago), licensed Apache-2.0. It adds 175 tokens to every session and 2,695 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
token-saver-config
Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.
sdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
loadout-import-workflow
Import another repo's command/skill suite into loadout as a workflow. Use when the user points at an agent framework, plugin, or command pack (e.g. a GitHub repo, a .claude/commands/ directory, a skills pack) and wants its process turned into a loadout [[workflows]] entry — "import this workflow", "turn this plugin…
loadout-migrate
Migrate existing global AI agent instructions into loadout. Use when adopting loadout, importing a CLAUDE.md / AGENTS.md / global agent rules into loadout, setting up /.config/loadout/config.toml, or turning prose agent instructions into reusable fragments and stack-targeted profiles.
loadout-remember
Save a durable, cross-project user preference into loadout's global fragments/profiles — or update the fragment it contradicts. Use when the user states lasting guidance that should follow them across projects and agents ("always X", "never Y", "stop doing Z"), especially when it conflicts with guidance the loadout…
orchestrator
Use this skill when running as an ephemeral orchestrator subagent for a Taniwha project. The skill instructs the agent to read project state from disk, decide the single next action the dispatcher should take, write that decision back to disk, and exit. Trigger this whenever the dispatcher has invoked an orchestrator…