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 commands/karkranikhil/sf-ai-toolkit/write-testsgit clone --depth 1 https://github.com/karkranikhil/sf-ai-toolkitWrote 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/karkranikhil/sf-ai-toolkit/write-tests)<a href="https://agentmods.dev/commands/karkranikhil/sf-ai-toolkit/write-tests"><img src="https://agentmods.dev/badge/commands/karkranikhil/sf-ai-toolkit/write-tests.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 | $0.00000 | $0.00222 |
| Opus 5 | $0.00000 | $0.00111 |
| Sonnet 5 | $0.00000 | $0.00044 |
| Haiku 4.5 | $0.00000 | $0.00022 |
Grade A, and why
write-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 3d 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.
What it actually says
/write-tests
Create or update Apex tests and LWC tests for the specified code.
For Apex tests
- Read the existing class or trigger being tested.
- Identify the main scenarios: positive, negative, bulk (200+ records), security.
- Create or update the test class using this structure:
@TestSetupfor shared test data- Individual test methods for each scenario
Test.startTest()/Test.stopTest()around DML
- Do not use
SeeAllData=true. - Cover at least: positive case, null/empty inputs, bulk (200 records), with/without sharing.
For LWC Jest tests
- Read the component JS file.
- Create a Jest test file that:
- Tests initial render
- Tests user interactions
- Mocks wire adapters and Apex calls
- Tests error states
- Follow the patterns in the existing
__tests__folders.
Output
Provide the complete test file(s). State the expected coverage improvement.
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.
- 3d ago First seen · 29 lines · 0 tokens per session scan A 83f3bc566969
write-tests is a command published in the GitHub repository karkranikhil/sf-ai-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 222 tokens. 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 commands, from other repositories
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
unit-test
Write / run the unit tests for the feature. (AIDLC Unit Test phase) Usage: /unit-test.
verify-tests
Run comprehensive test verification to ensure all tests pass before committing or merging.
quality-check-command
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.
test
Generate tests for the specified code or feature.
test
Generate comprehensive tests.