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 genudo-ai/genudo_mcp --skill generate-test-journeysgit clone --depth 1 https://github.com/genudo-ai/genudo_mcpWrote 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/genudo-ai/genudo_mcp/generate-test-journeys)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/generate-test-journeys"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/generate-test-journeys/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/genudo-ai/genudo_mcp/generate-test-journeys"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/generate-test-journeys.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 | $0.00094 | $0.01130 |
| Opus 5.5 | $0.00038 | $0.00452 |
| Sonnet 5.5 | $0.00019 | $0.00226 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
generate-test-journeys 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Test Journeys
Write journeys that behave like real customers and assert behaviour, not wording. Output is a
suite JSON the genudo-agent-testing-engine runs (see run-agent-tests); its
templates/starter-suite.json is the reference example.
1. Gather the ground truth
- Facts: prices, offers, shipping fees and times, payment methods, policies, links.
Pull them from the knowledge tables (
list_knowledge_tables,search_knowledge_table) and confirm anything ambiguous with the user. Facts become the suite'sfactstext — the judge grades against it, so it must be exact. - Flow:
list_pipeline_stagesfor stage names and enter conditions;list_actionsfor the action names a step can expect (e.g. the order or support webhook). - Demand: the
mine-customer-chatsreport — cluster shares set how many journeys each intent gets; verbatim openers become first messages. - Incidents: every real failure the user reports becomes a journey with
source_incident.
2. Design rules
- 4–12 steps per journey. Single-turn checks miss state bugs.
- One consistent persona per journey; later turns reuse earlier details (city, size, payment choice) without restating them. Write in the customers' real language and dialect, including the misspellings mining surfaced.
- Assert behaviour, not wording — numbers, required elements, the action, the stage. Never assert a full verbatim reply.
- Priorities: P0 = main sales path, order capture, payment, safety, top-volume intents (a P0 failure blocks release); P1 = edge cases, modifications, support; P2 = style and rare phrasings.
- Cover the negatives: customer gives an address only to ask shipping (no order must fire), objects to price (no invented discount), changes their mind, sends a blurry or unrelated image, asks something the business doesn't do.
3. Suite format
suite: version, agent_name, brand_terms[], facts, global_rules[], cases[]
case: case_id (J01…), short_name, contact_name, category, priority (P0|P1|P2),
pipelines ("messenger,instagram" or "all"), start_stage, description,
source_incident, steps[]
step: step_no, customer_message, image (fixture path, optional), expected_reply (human
reference), must_contain_all / must_contain_any / must_not_contain ("||"-separated),
regex_must, regex_forbidden, expect_action (action name | none),
expect_payload_contains, expect_stage, expect_stage_not, judge_rubric,
severity (critical|major|minor), language (ar|en)
rule: rule_id, description, type, pattern, exempt_if_reply_contains, severity, category
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.
- 6d ago First seen · 85 lines · 94 tokens per session scan A e79719573020
generate-test-journeys is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 94 tokens to every session and 1,130 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 2026-10-11.
Other skills, from other repositories
playwright-browser
Use when automating browsers, testing pages, taking screenshots, checking UI, verifying login flows, or testing responsive behavior.
local-e2e
A skill for running end-to-end tests against a local LeadAce application stack. End-to-end tests check complete user flows across the running application, rather than only testing individual pieces.
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…
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.
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.