vigilbase.com publishes machine-readable files so AI agents can find the tools and learn how to run them. Every file below is public and needs no key.
Agent skills
Each tool has a skill: a Markdown file that describes what the tool checks, its inputs, its outputs and how to run it through the Agent API, the CLI or the browser.
| File | Contents |
|---|---|
https://vigilbase.com/.well-known/agent-skills/index.json | The skills index. Each entry has a name, type (skill-md), description, url and a sha256: digest of the skill file. |
https://vigilbase.com/agent-skills/{slug}.md | One skill, as text/markdown. |
The skills published are:
| Slug | Tool |
|---|---|
website-security | Website Security |
email-security | Email security |
cloudflare-checkup | Cloudflare Checkup |
security-headers | Security headers |
fortibleed-check | FortiBleed |
react2shell | React2Shell |
A skill being published does not mean the tool is on the Agent API: only security-headers and email-security are. The others explain how to run the tool in the browser or through Vigilbase One.
The index and skills are cached for about 5 minutes. Use the digest to tell whether a skill has changed.
From the CLI, print a skill with vigilbase skill <tool>, or a tool's description and target format with vigilbase describe <tool>.
Other discovery files
| File | Contents |
|---|---|
https://vigilbase.com/llms.txt | A plain-text summary of Vigilbase and its tools for language models. |
https://vigilbase.com/openapi.json | The OpenAPI 3.1 document for the public API: badges, the tool catalog and the two execute endpoints. Shown on API reference. |
https://vigilbase.com/.well-known/api-catalog | A linkset that points to the OpenAPI document and the developer documentation. |
https://vigilbase.com/.well-known/ai-catalog.json | A capability manifest that lists the public API and every published skill. |
https://vigilbase.com/.well-known/mcp/server-card.json | A placeholder MCP server card. |