Borrowing it
Nothing to install: this file belongs to Hafeok/product-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Hafeok/product-cli/main/.claude/skills/feature-e2e/SKILL.mdgit clone --depth 1 https://github.com/Hafeok/product-cliWrote 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/hafeok/product-cli/feature-e2e)<a href="https://agentmods.dev/skills/hafeok/product-cli/feature-e2e"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/feature-e2e/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/hafeok/product-cli/feature-e2e"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/feature-e2e.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 | $0.00105 | $0.02364 |
| Opus 5.5 | $0.00042 | $0.00946 |
| Sonnet 5.5 | $0.00021 | $0.00473 |
| Haiku 4.5 | $0.00011 | $0.00236 |
Grade C, and why
feature-e2e scanned grade C with 1 finding 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/<feature-slug>-e2e-test How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature End-to-End Test
This skill runs a real-world end-to-end shake-out of a Product CLI feature against a fresh, isolated repo, driven entirely through the CLI. The goal is to confirm that a feature works for a brand-new user — not just that the unit tests pass.
The CLI is the canonical user-facing surface. The MCP server is a transport over the same logic. If the feature has an MCP-only surface (e.g. it adds an MCP tool with no CLI equivalent), test that too — but only after the CLI surface is fully exercised.
When to use
- The user asks to do a "thorough end-to-end test" of a specific feature ID
- A feature has just been implemented and needs human-style validation
- You suspect drift between PRD/ADR text and the actual binary behaviour
What to do
1. Read the feature spec first
Open docs/features/FT-XXX-*.md. Extract:
- The acceptance criteria list — these become your test plan
- The CLI surface — every subcommand and flag the feature adds, plus existing commands whose behaviour the feature changes
- The error codes — each
EXXhas a path that should fire - Any config keys the feature reads (
product.tomlsections) - Any resolution paths the feature uses (e.g. repo → user → built-in)
2. Use the existing release binary
PRODUCT=/abs/path/to/repo/target/release/product
[ -x "$PRODUCT" ] || cargo build --release
Don't rebuild if a release binary already exists — the bottleneck is the test work, not compilation.
3. Create a clean tmp scratch directory
rm -rf /tmp/<feature-slug>-e2e-test
mkdir -p /tmp/<feature-slug>-e2e-test
cd /tmp/<feature-slug>-e2e-test
Always start clean — the resolution order for templates / config / .product/ directory walks up the filesystem, so a stale parent state can leak into the test.
4. Initialise a fresh project via the CLI
$PRODUCT init -y --name ft-xxx-e2e-test
Defaults to the canonical .product/ layout (ADR-048). Pass --legacy-layout only if the feature specifically needs the pre-FT-057 root-based layout.
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.
- 1mo ago First seen · 190 lines · 105 tokens per session scan C b1012edc8ffe
feature-e2e is a skill published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 2,364 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.