Borrowing it
Nothing to install: this file belongs to incubateur-ademe/benefriches. 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/incubateur-ademe/benefriches/main/.agents/skills/run-e2e-tests/SKILL.mdgit clone --depth 1 https://github.com/incubateur-ademe/benefrichesWrote 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/incubateur-ademe/benefriches/run-e2e-tests)<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/run-e2e-tests"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/run-e2e-tests/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/incubateur-ademe/benefriches/run-e2e-tests"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/run-e2e-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00112 | $0.00860 |
| Opus 5.5 | $0.00045 | $0.00344 |
| Sonnet 5.5 | $0.00022 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run E2E Tests
Run Playwright against an isolated e2e stack. A stack belongs to a port slot (0-99): the slot sets every host port and the compose project name, so stacks of different worktrees run side by side. node adws/env.ts up <slot> writes .e2e-stack at the repository root (web, API and mail catcher URLs, ports, DATABASE_URL, COMPOSE_PROJECT_NAME); Playwright reads it, so the tests hit that stack.
Arguments
$ARGUMENTS(optional): Test path filter passed toplaywright test(e.g.,tests/create-site/,tests/create-project/create-photovoltaic-project.spec.ts)
Procedure
Run every command from the repository root (the worktree root). Stop and report on failure at any step.
1. Get a stack
If .e2e-stack exists, a stack is already up for this worktree (for example started by the ADW runner): cat .e2e-stack, use it, and skip step 3: its owner tears it down.
Otherwise bring one up. Pick a slot no other worktree uses (docker ps --format '{{.Names}}' | grep benefriches-e2e- lists the slots in use); default to $E2E_SLOT, else 1. Slot 0 uses the same ports as make e2e-up.
node adws/env.ts up <slot>
It installs dependencies, builds shared, builds and starts the stack with a fresh database, health-checks the web app, API, database and mail catcher, then prints JSON:
"outcome": "ready": the stack is up and.e2e-stackis written."outcome": "env-failed":step,commandandoutputsay what failed (service logs are appended for compose and health-check failures); the half-started stack has already been removed. Report it and stop: this is an environment problem, not a test failure. If a port is taken, retry with another slot. The full output of every step is in.e2e-stack.log.
2. Run the tests
pnpm --filter e2e-tests test:headless $ARGUMENTS
To watch a failing test, rerun it with the browser visible: pnpm --filter e2e-tests test:headed <path> (append --debug for the Playwright inspector). The stack must still be up.
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.
- 9d ago Changed · +7 lines · +15 tokens per session 45915d85b5c3
- 1mo ago Changed · +1 lines cf78ea38aa95
- 2mo ago First seen · 53 lines · 97 tokens per session scan A c7e0e87c80ec
run-e2e-tests is a skill published in the GitHub repository incubateur-ademe/benefriches (45 stars, last pushed today), licensed MIT. It adds 112 tokens to every session and 860 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 2026-08-30.
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.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.