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/soden46/engineer-flow/testingnpx skills add soden46/engineer-flow --skill testinggit clone --depth 1 https://github.com/soden46/engineer-flowWhat 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 | $0.00028 | $0.00867 |
| Opus 5 | $0.00014 | $0.00434 |
| Sonnet 5 | $0.00006 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
testing 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing
Use this skill when work requires automated verification, regression protection, test design, or test maintenance.
This skill is language and framework agnostic.
Principles
Test observable behavior rather than internal implementation details whenever practical.
Prefer the smallest test scope that gives useful confidence.
Use:
- unit tests for isolated logic
- integration tests for boundaries between components
- contract tests for external interfaces
- end-to-end tests only where broader system behavior must be proven
Do not require every behavior to be tested at every layer.
Browser E2E Playwright Regression
Use browser or end-to-end regression tests when important behavior can only be proven through the rendered application, real navigation, browser state, client-side interactions, or frontend/backend wiring.
Browser regression coverage may be appropriate for:
- critical user journeys
- form validation and submission behavior
- authentication-dependent navigation
- frontend/backend contract wiring
- client-side state transitions
- browser-only rendering failures
- responsive behavior that has broken before
- accessibility-critical interaction paths
Use the project's existing browser test tool when available. Playwright is a good default when the project already uses it or when the user asks for it, but do not introduce it solely because a browser was useful for manual inspection.
Prefer resilient user-facing locators, deterministic setup, web-first assertions, and scoped traces or screenshots that help diagnose failures.
Visual Responsive Checks
Visual and responsive verification can be manual, scripted, or snapshot-based depending on project risk and existing tooling.
Verify relevant viewports, states, and interactions without creating brittle snapshot tests for every cosmetic detail.
Use visual snapshots only when the project already supports them or when the changed surface justifies the maintenance cost.
When a UI is reconstructed from a reference, convert only stable accepted behavior into durable tests. Do not encode third-party branding, exact marketing text, or incidental reference-site content as regression requirements unless the user explicitly owns or requires it.
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 · 164 lines · 28 tokens per session scan A 969f62190e7c
testing is a skill published in the GitHub repository soden46/engineer-flow (3 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 867 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
clarify
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates automatically when ambiguity persists.
review
Multi-agent code review for Rust CLI/TUI. UX Review inactive (terminal UI — no web frontend). Code Review only. Includes Rust/clippy-specific checklist.