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/bloombooks/bloomdesktop/bloom-canvas-e2e-testingnpx skills add BloomBooks/BloomDesktop --skill bloom-canvas-e2e-testinggit clone --depth 1 https://github.com/BloomBooks/BloomDesktopWrote 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/bloombooks/bloomdesktop/bloom-canvas-e2e-testing)<a href="https://agentmods.dev/skills/bloombooks/bloomdesktop/bloom-canvas-e2e-testing"><img src="https://agentmods.dev/badge/skills/bloombooks/bloomdesktop/bloom-canvas-e2e-testing.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00908 |
| Opus 5 | $0.00015 | $0.00454 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
bloom-canvas-e2e-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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use this skill when the user wants automated Playwright tests (not manual devtools reproduction) for Canvas Tool behavior.
This skill is for:
- creating and maintaining
bookEdit/canvas-e2e-teststests - verifying drag/drop and canvas interactions with real mouse gestures
- running focused Canvas E2E checks against Bloom Edit Tab
This skill is not for:
- manual-only reproduction (use the manual canvas tool testing skill)
- component-harness tests under
react_components/*/*.uitest.ts
Required context
- Bloom is running and serving Edit Tab at
http://localhost:8089/bloom/CURRENTPAGE - Current page includes
.bloom-canvas - Canvas tool is available in toolbox
- Playwright runtime dependencies are installed in:
src/BloomBrowserUI
Primary URL
http://localhost:8089/bloom/CURRENTPAGE
Runtime and command model
Use the src/BloomBrowserUI package and run the canvas suite via the root e2e script.
- Install once (or when deps change):
cd src/BloomBrowserUIpnpm install
- Run one canvas test:
cd src/BloomBrowserUIpnpm e2e canvas specs/01-toolbox-drag-to-canvas.spec.ts
- Run the full canvas suite:
cd src/BloomBrowserUIpnpm e2e canvas
Frame model (critical)
Bloom Edit Tab has multiple iframes. Use frame names first:
- Toolbox frame:
- name:
toolbox - URL usually includes
toolboxContent
- name:
- Editable page frame:
- name:
page - URL usually includes
page-memsim-...htm
- name:
- Do not treat top
CURRENTPAGEframe as editable page content.
Reliable selectors and activation
- Canvas tool tab header:
h3[data-toolid="canvasTool"] - Canvas tool root:
#canvasToolControls - Canvas surface:
.bloom-canvas - Created elements:
.bloom-canvas-element - Speech/comic palette item:
img[src*="comic-icon.svg"]
Before clicking the canvas tool header, first check whether #canvasToolControls is already visible.
Drag/drop requirements
- Use real Playwright mouse gestures (
page.mouse.down/move/up), not synthetic dispatched drag events. - Prefer distinct drop points.
- Verify outcomes semantically:
- element count increase (
.bloom-canvas-element) - position/rect checks where relevant
- element count increase (
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.
- 5d ago First seen · 100 lines · 30 tokens per session scan A b17f3a705667
bloom-canvas-e2e-testing is a skill published in the GitHub repository BloomBooks/BloomDesktop (44 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 908 once invoked, about $0.0002 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
run-integration-tests
Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.
cli-e2e-testcase-writer
Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
harness-test-writer
Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…
agent-device-evidence
Records iOS/Android native MP4 evidence for test/repro flows extracted from an Expensify GitHub PR or issue. Use when the user asks to "record the flow for PR.