Borrowing it
Nothing to install: this file belongs to BloomBooks/BloomDesktop. 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/BloomBooks/BloomDesktop/master/.github/prompts/bloom-component-test.prompt.mdgit 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/commands/bloombooks/bloomdesktop/bloom-component-test)<a href="https://agentmods.dev/commands/bloombooks/bloomdesktop/bloom-component-test"><img src="https://agentmods.dev/badge/commands/bloombooks/bloomdesktop/bloom-component-test.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 5.1 | $0.00003 | $0.00516 |
| Opus 5 | $0.00002 | $0.00258 |
| Sonnet 5 | $0.00001 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
bloom-component-test 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 today.
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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
We have a test system explained at src/BloomBrowserUI/react_components/component-tester/README.md.
First, decide if we are in the Setup or Implementation stage.
Setup Stage
If you do not see a component_tests/ directory, it means we are not set up yet. For an example, look at src/BloomBrowserUI/react_components/registration and src/BloomBrowserUI/react_components/registration/component-tests as an example. You need to intercept some api calls using src/BloomBrowserUI/react_components/component-tester/apiInterceptors.ts. In the directory of the component (not in component-tests/), create test.sh and manual.sh scripts to run the tests and open the component in a browser for manual testing.If it doesn't exist already, make a -ui-test-plan.md for this. Keeps it small-- during setup we are not ready for complete testing, but proving that you can make the component show in a browser and do one minimal thing. Later, I will direct you to to add more tests to the plan, but not now. Once you have the plan, work your way through it, checking off items as you go, running the tests along the way.
- If you are unclear about how to organize tests in different files, make a proposal and ask me.
Implementation Stage
Troubleshooting
If you need to see what the browser sees, you may use the chrome-devtools mcp. You can access the console, take screenshots, and inspect elements. If you don't have access to that mcp, ask me to install/enable it.
Refactoring to make testing easier
Sometimes the top level component is not readily testable. In that case it might be appropriate to refactor out a core that is easily testable. Do not do this without discussing it with me first. Just stop and make a proposal. Do not refactor any code except for the test code itself without prior approval.
Guidelines for writing the tests
- If you want to make a mock, stop and ask me.
- Avoid using timed waits like page.waitForTimeout(1000). If there is no other way, you must discuss it with me first and then if I approve, document why it is necessary in a comment.
- Feel free to add data-test-id attributes to elements in the component under test to make them easier to find. Avoid using css to finding things.
- Keep the tests well factored with common code going to a test-helpers.ts file.
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.
- today First seen · 26 lines · 3 tokens per session scan A 92e62efc1b03
bloom-component-test is a command published in the GitHub repository BloomBooks/BloomDesktop (44 stars, last pushed yesterday), licensed MIT. It adds 3 tokens to every session and 516 once invoked, about $0.0000 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 2026-09-06.
Other commands, from other repositories
test-bar
Generate a floating QA test overlay for the current branch's UI changes. Use when user says /test-bar, needs visual QA scenarios, or wants to test conditional rendering paths.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
zephyr-coverage-analysis
Analyze Zephyr test case coverage for a Jira user story and produce a QE management report with metrics, risk scoring, and prioritized recommendations.
build-from-figma
You are the master orchestrator for converting a Figma design into a fully working, tested React application. You receive a Figma URL and guide the entire process through 9 phases, using specialized skills and agents.
caracterizar-prompt
Characterization de prompts/tools LLM em produção — temperature=0 + seed fixo + sanitização específica. Trata prompts como código legacy. Modernização 2026 sem precedente em 2004.
prompt-eval-debug
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.