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 skills add RasaHQ/rasa-agent-skills --skill rasa-writing-e2e-testsgit clone --depth 1 https://github.com/RasaHQ/rasa-agent-skillsWrote 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/rasahq/rasa-agent-skills/rasa-writing-e2e-tests)<a href="https://agentmods.dev/skills/rasahq/rasa-agent-skills/rasa-writing-e2e-tests"><img src="https://agentmods.dev/badge/skills/rasahq/rasa-agent-skills/rasa-writing-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/rasahq/rasa-agent-skills/rasa-writing-e2e-tests"><img src="https://agentmods.dev/badge/skills/rasahq/rasa-agent-skills/rasa-writing-e2e-tests.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 | $0.00053 | $0.02229 |
| Opus 5.5 | $0.00021 | $0.00892 |
| Sonnet 5.5 | $0.00011 | $0.00446 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
rasa-writing-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 2mo 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing E2E Tests in Rasa
E2E tests validate the assistant as a whole system — from user message to bot response,
including flow execution, slot filling, custom actions, and generative responses. They
live as YAML files in the tests/ directory and run via rasa test e2e.
Workflow
- Identify the conversation scenario to test (happy path, edge case, error path).
- Review existing tests — extend before creating new ones.
- Create or open a YAML file under
tests/(see "File organization"). - Write the test case with
usersteps and expected outcomes (see "Writing test cases"). - Add assertions for detailed validation if needed (see "Assertions").
- Set up fixtures if the test requires pre-filled slots (see "Fixtures").
- Stub custom actions if needed to avoid external calls (see "Stubbing custom actions").
- Run tests with
rasa test e2e(see "Running tests").
Key principles
- One test case per scenario: happy path, cancellation, validation failure, etc.
- Start with a
userstep: the test runner begins evaluation afteraction_session_start. - Alternate
userand expected outcomes: avoid consecutiveusersteps. - Use assertions for CALM-specific checks:
flow_started,flow_completed,action_executedgive stronger guarantees than matching bot text. - Use
botoruttersteps for simple cases: when you only need to verify the response text or domain response name. - Use fixtures to avoid repetitive setup: shared context like authentication goes
in
conftest.yml.
File organization
Test files live under tests/ and are automatically discovered by Rasa. Subdirectories
are supported — pass the path as a positional argument to rasa test e2e.
tests/
├── e2e_test_cases.yml # default test file
├── conftest.yml # shared fixtures (visible to all tests)
├── booking/
│ ├── conftest.yml # fixtures scoped to this directory
│ ├── test_book_trip.yml
│ └── test_cancel_booking.yml
└── payments/
└── test_process_payment.yml
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.
- 2mo ago First seen · 262 lines · 53 tokens per session scan A d9cdf938fe05
rasa-writing-e2e-tests is a skill published in the GitHub repository RasaHQ/rasa-agent-skills (6 stars, last pushed 29d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,229 once invoked, about $0.0002 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.
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.