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 agentmods add skills/haposoft/cafekit/web-testingnpx skills add haposoft/cafekit --skill web-testinggit clone --depth 1 https://github.com/haposoft/cafekitWhat 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 | $0.00052 | $0.00886 |
| Opus 5 | $0.00026 | $0.00443 |
| Sonnet 5 | $0.00010 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
hapo:web-testing 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/accessibility-testing.md 1.9 KB
- references/api-testing.md 1.8 KB
- references/ci-cd-testing-workflows.md 2.5 KB
- references/component-testing.md 2.4 KB
- references/contract-testing.md 3.3 KB
- references/cross-browser-checklist.md 1.7 KB
- references/database-testing.md 3.3 KB
- references/e2e-testing-playwright.md 2.7 KB
- references/functional-testing-checklist.md 2.7 KB
- references/interactive-testing-patterns.md 2.5 KB
- references/load-testing-k6.md 1.7 KB
- references/mobile-gesture-testing.md 2.1 KB
- references/performance-core-web-vitals.md 3.1 KB
- references/playwright-component-testing.md 2.8 KB
- references/pre-release-checklist.md 1.8 KB
- references/security-checklists.md 2.5 KB
- references/security-testing-overview.md 2.8 KB
- references/shadow-dom-testing.md 1.6 KB
- references/test-data-management.md 2.9 KB
- references/test-flakiness-mitigation.md 1.8 KB
- references/testing-pyramid-strategy.md 2.1 KB
- references/unit-integration-testing.md 2.7 KB
- references/visual-regression.md 2.2 KB
- references/vulnerability-payloads.md 1.3 KB
- scripts/analyze-test-results.js 7.8 KB runs code
- scripts/init-playwright.js 6.5 KB runs code
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.
- 2d ago First seen · 103 lines · 52 tokens per session scan A b2781e023db2
hapo:web-testing is a skill published in the GitHub repository haposoft/cafekit (54 stars, last pushed 3d ago), with no licence file. It adds 52 tokens to every session and 886 once invoked, about $0.0003 per session on Opus 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
Playwright Browser Automation
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions…
ai-native-workflow
Sole entry-point router for AI-assisted work on this Playwright scaffold — owns the 8-phase main workflow (classify → route → explore → plan+confidence → human gate → apply → verify → report), the human↔agent conversation contract, the routing matrix that picks the right specialized skill, and the confidence-gate…
data-strategy
Test data strategy for the Playwright scaffold — Faker + Zod factories for dynamic happy-path data, static TS files (.ts with as const exports — never .json) for domain-specific curated invalid sets, and the universal type-mismatch arrays in test-data/static/util/invalid-values.ts. Use when creating or editing a data…
config
Configuration and environment variable conventions for the Playwright scaffold — env file layout (env/.env.), dotenv loading via playwright.config.ts and the ENVIRONMENT variable, config objects in config/app.ts and config/util/util.ts, and the rules for adding new env-driven values. Use when adding a new environment…
refactor-values
Safe refactoring workflow for enum values, enum keys, and static test data in test-data/static/.ts — mandatory impact analysis, cascading updates, and verification. Use BEFORE changing any enum member's string value (ApiEndpoints., Messages., Roles, StorageStatePaths), renaming any enum key, or editing any existing…
e2e-testing
End-to-end testing for Falcon Foundry apps using Playwright and @crowdstrike/foundry-playwright. TRIGGER when user asks to "add e2e tests", "add playwright tests", "write end-to-end tests", "test my app", or mentions "e2e", "playwright", or "end-to-end" in the context of testing a Foundry app. DO NOT TRIGGER during…