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/product-session-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/product-session-e2e)<a href="https://agentmods.dev/skills/hafeok/product-cli/product-session-e2e"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/product-session-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/product-session-e2e"><img src="https://agentmods.dev/badge/skills/hafeok/product-cli/product-session-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 | $0.00090 | $0.00665 |
| Opus 5.5 | $0.00036 | $0.00266 |
| Sonnet 5.5 | $0.00018 | $0.00133 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
product-session-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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Session — end-to-end shake-out
Confirms the product-what / product-how / product-build skills still work as a set against a brand-new repo, driven entirely through the CLI (the canonical surface; the MCP tools are a transport over the same logic). Run it whenever the tool surface changes.
Run it
bash scripts/checks/session-e2e.sh # uses target/debug/product
PRODUCT=/abs/path/to/product bash scripts/checks/session-e2e.sh # pin a binary
The script is self-contained: it makes a fresh tmp repo, runs the sequence below,
prints PASS/FAIL per step, and exits non-zero if any step or assertion fails.
What it drives (each phase skill's worked example)
- init —
product init --demo --yes --name bookstore(seeds the What). - product-what —
domain validate→domain new value-object→ re-validate. - product-how —
how init→how add decision|principle|pattern(the principle is--enforced-byso it earns its place, §4.1) →how set app-contract→how validate→archetype init→cell init→cell dispatch --bind entity=Order(produces a real work unit). - product-build —
slice new→deliverable new(acceptance asid: statement, §7.2) →build --dry-run. - assertions — the build run-plan uses the dispatched work unit
(
handler-order, not a fallback) and the gate reports domain conformance.
When it fails
Each FAIL prints the offending command's last lines. Common causes:
- A renamed/removed tool or flag → update the matching phase skill and this script together (they must stay in lockstep).
- A new conformance rule (e.g. §4.1 earn-their-place) the worked example trips → fix the example to satisfy it, then mirror the fix in the phase skill.
Note on session gating
This runs the CLI, which has no phase lock, so it exercises the underlying
capability rather than the gated ordering. Inside a real product mcp --workflow
session the phases gate the tools — in particular cell dispatch / work-unit
authoring are How-phase and freeze in Build, so a session must dispatch work
units before advancing (see product-how / product-build).
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 · 56 lines · 90 tokens per session scan A 404e50300964
product-session-e2e is a skill published in the GitHub repository Hafeok/product-cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 665 once invoked, about $0.0004 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 2026-08-31.
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.