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.
git clone --depth 1 https://github.com/rohittcodes/claude-plugin-suiteWrote 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/rohittcodes/claude-plugin-suite/test)<a href="https://agentmods.dev/commands/rohittcodes/claude-plugin-suite/test"><img src="https://agentmods.dev/badge/commands/rohittcodes/claude-plugin-suite/test/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/commands/rohittcodes/claude-plugin-suite/test"><img src="https://agentmods.dev/badge/commands/rohittcodes/claude-plugin-suite/test.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 | $0.00007 | $0.00323 |
| Opus 5.5 | $0.00003 | $0.00129 |
| Sonnet 5.5 | $0.00001 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
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 1mo 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
Test Execution Command
Execute comprehensive test suite with detailed reporting and coverage analysis.
Context
- Test type: $1 (unit|integration|e2e|all - default: all)
- Coverage threshold: $2 (default: 80%)
- Current test files: !
find . -name "*test*" -o -name "*spec*" | head -10 - Test configuration: @package.json
Test Execution Strategy
1. Unit Tests
- Run isolated component tests
- Validate business logic
- Check error handling
- Measure code coverage
2. Integration Tests
- Test component interactions
- Validate API endpoints
- Check database operations
- Test external service integrations
3. End-to-End Tests
- Full user workflow testing
- Cross-browser compatibility
- Performance validation
- Accessibility compliance
4. Test Reporting
- Generate detailed test reports
- Coverage analysis and visualization
- Performance metrics
- Failure analysis and recommendations
Quality Gates
- All tests must pass
- Coverage must meet $2% threshold
- No critical security vulnerabilities
- Performance benchmarks within limits
Expected Outcome
- Complete test execution report
- Coverage analysis with recommendations
- Performance metrics and benchmarks
- Actionable feedback for improvements
Failure Handling
If tests fail:
- Detailed failure analysis
- Root cause identification
- Suggested fixes and improvements
- Priority-based remediation plan
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.
- 1mo ago First seen · 60 lines · 0 tokens per session scan A 8cfc98e7ff79
test is a command published in the GitHub repository rohittcodes/claude-plugin-suite (29 stars, last pushed 1y ago), licensed MIT. It adds 7 tokens to every session and 323 once invoked, about $0.0000 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 2026-09-21.
test compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| testrohittcodes/claude-plugin-suite | Command | 29 | 1y ago | MIT | A | 7 | Claude Code |
| test-suitetravisjneuman/.claude | Command | 112 | 5d ago | MIT | A | 7 | Claude Code |
| gsd:add-testskryptobaseddev/cleo | Command | 159 | today | MIT | A | 18 | Claude Code |
| testfelvieira/claude-skills-fv | Command | 28 | 5d ago | Apache-2.0 | A | 14 | Claude Code |
| quality-check-commandKazuki-tam/next-stage | Command | 12 | 17d ago | MIT | A | 0 | Claude Code, Cursor |
| testterrene-foundation/kailash-coc-claude-py | Command | 13 | 2mo ago | Apache-2.0 | A | 0 | Claude Code |
| verifyeddiebelaval/squire | Command | 21 | 3mo ago | MIT | A | 0 | Claude Code |