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/vantainc/vanta-mcp-plugin/list-testsnpx skills add VantaInc/vanta-mcp-plugin --skill list-testsgit clone --depth 1 https://github.com/VantaInc/vanta-mcp-pluginWrote 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/vantainc/vanta-mcp-plugin/list-tests)<a href="https://agentmods.dev/skills/vantainc/vanta-mcp-plugin/list-tests"><img src="https://agentmods.dev/badge/skills/vantainc/vanta-mcp-plugin/list-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 | $0.00016 | $0.00731 |
| Opus 5 | $0.00008 | $0.00365 |
| Sonnet 5 | $0.00003 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
list-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 4d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Show the user their failing Vanta tests, ranked by what the plugin can help with.
Steps
- Fetch failing tests. Call
teststo get all tests with statusNEEDS_ATTENTION. - Categorize and rank tests. Group the failing tests into tiers:
Ready to fix — Tests where:
- The test's integration matches resources likely managed in this repo. Detect this by checking for deployment code: look for provider declarations (
provider "aws"in.tffiles for AWS,provider "google"for GCP,provider "azurerm"for Azure) and resource type prefixes (aws_,google_,azurerm_) in.tffiles; orAWSTemplateFormatVersionin CloudFormation templates; orcdk.jsonfor CDK projects. Use both signals — provider blocks are often absent in child modules or Terragrunt configs. - Present these first. These are one-command fixes with
/vanta:fix-test <testId>. Fixable with guidance — Tests that are code-remediable but may not match this repo (different cloud provider, different integration). The user can still get remediation code, but may need to apply it elsewhere. Manual steps needed — Tests that require configuration changes in external tools, Vanta settings, or manual processes. The plugin can provide guidance but not generate code.
- The test's integration matches resources likely managed in this repo. Detect this by checking for deployment code: look for provider declarations (
- Present the results. For each tier, show a table with columns:
- Test name
- Test ID
- Number of failing entities
- Integration (e.g., AWS, GitHub, Azure)
- How long the test has been failing (from
latestFlipDate) - For "Ready to fix" tests, show:
Run /vanta:fix-test <testId> to generate a PR
- Highlight co-failure clusters. If multiple failing tests map to the same resource type or integration, note this. For example: "5 IAM tests are failing — fixing the password policy may resolve all of them at once."
- Keep it scannable. Use a table or bulleted list. Do not dump raw API responses. The user needs to quickly see what to fix first.
Edge cases
- No failing tests: "All tests are passing. Nice work." Do not show an empty table.
- User asks to filter (e.g., "show AWS tests"): Filter by integration name. If no failures match the filter, say so and show the full list: "No failing AWS tests found. Here's what is failing across other integrations:"
- User asks to filter by framework (e.g., "SOC 2 gaps"): Filter by framework. "You have [N] failing tests mapped to SOC 2. Here are the ones I can help fix from this repo."
- User asks "what should I fix first?": Rank by impact: IaC-fixable in this repo first, then highest entity count, then longest time failing. Highlight co-failure clusters as "biggest bang for the buck."
- Very large number of failing tests: Group by integration and summarize counts rather than listing every test. Show the top 5-10 highest-impact items with a note: "[N] more tests failing. Want to see the full list or focus on [integration]?"
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.
- 4d ago First seen · 32 lines · 16 tokens per session scan A e725a61375c9
list-tests is a skill published in the GitHub repository VantaInc/vanta-mcp-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 731 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…