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 skills add patricio0312rev/skillset --skill bruno-collection-generatorgit clone --depth 1 https://github.com/patricio0312rev/skillsetWrote 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/patricio0312rev/skillset/bruno-collection-generator)<a href="https://agentmods.dev/skills/patricio0312rev/skillset/bruno-collection-generator"><img src="https://agentmods.dev/badge/skills/patricio0312rev/skillset/bruno-collection-generator/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/skills/patricio0312rev/skillset/bruno-collection-generator"><img src="https://agentmods.dev/badge/skills/patricio0312rev/skillset/bruno-collection-generator.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 | $0.00074 | $0.03544 |
| Opus 5 | $0.00037 | $0.01772 |
| Sonnet 5 | $0.00015 | $0.00709 |
| Haiku 4.5 | $0.00007 | $0.00354 |
Grade A, and why
bruno-collection-generator 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 9d 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.
This is a copy
100% identical to bruno-collection-generator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 675 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bruno Collection Generator
Generate Bruno collection files for the open-source, Git-friendly API client.
Core Workflow
- Scan routes: Find all API route definitions
- Extract metadata: Methods, paths, params, bodies
- Create collection: Initialize bruno.json manifest
- Generate .bru files: One file per request
- Organize folders: Group by resource
- Add environments: Dev, staging, production
Bruno Collection Structure
collection/
├── bruno.json # Collection manifest
├── environments/
│ ├── Development.bru
│ ├── Staging.bru
│ └── Production.bru
├── users/
│ ├── folder.bru
│ ├── get-users.bru
│ ├── get-user.bru
│ ├── create-user.bru
│ ├── update-user.bru
│ └── delete-user.bru
├── auth/
│ ├── folder.bru
│ ├── login.bru
│ ├── register.bru
│ └── logout.bru
└── products/
├── folder.bru
└── ...
bruno.json Manifest
{
"version": "1",
"name": "My API",
"type": "collection",
"ignore": ["node_modules", ".git"]
}
.bru File Syntax
meta {
name: Get Users
type: http
seq: 1
}
get {
url: {{baseUrl}}/users
body: none
auth: bearer
}
auth:bearer {
token: {{authToken}}
}
query {
page: 1
limit: 10
}
headers {
Accept: application/json
}
docs {
Retrieve a paginated list of users.
}
Generator Script
// scripts/generate-bruno.ts
import * as fs from "fs";
import * as path from "path";
interface RouteInfo {
method: string;
path: string;
name: string;
description?: string;
body?: object;
queryParams?: { name: string; value: string }[];
auth?: boolean;
}
interface BrunoOptions {
collectionName: string;
outputDir: string;
baseUrl: string;
authType?: "bearer" | "basic" | "apikey";
}
function generateBrunoCollection(
routes: RouteInfo[],
options: BrunoOptions
): void {
const { outputDir, collectionName } = options;
// Create output directory
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
// Create bruno.json
const manifest = {
version: "1",
name: collectionName,
type: "collection",
ignore: ["node_modules", ".git"],
};
fs.writeFileSync(
path.join(outputDir, "bruno.json"),
JSON.stringify(manifest, null, 2)
);
// Create environments
generateEnvironments(outputDir, options);
// Group routes by resource
const groupedRoutes = groupRoutesByResource(routes);
for (const [resource, resourceRoutes] of Object.entries(groupedRoutes)) {
const folderPath = path.join(outputDir, resource);
if (!fs.existsSync(folderPath)) {
fs.mkdirSync(folderPath, { recursive: true });
}
// Create folder.bru
const folderBru = `meta {\n name: ${capitalize(resource)}\n}\n`;
fs.writeFileSync(path.join(folderPath, "folder.bru"), folderBru);
// Create request files
let seq = 1;
for (const route of resourceRoutes) {
const fileName = generateFileName(route);
const content = generateBruFile(route, seq++, options);
fs.writeFileSync(path.join(folderPath, `${fileName}.bru`), content);
}
}
}
function generateBruFile(
route: RouteInfo,
seq: number,
options: BrunoOptions
): string {
const lines: string[] = [];
// Meta section
lines.push("meta {");
lines.push(` name: ${route.name}`);
lines.push(" type: http");
lines.push(` seq: ${seq}`);
lines.push("}");
lines.push("");
// Request section
const method = route.method.toLowerCase();
const urlPath = route.path.replace(/:(\w+)/g, "{{$1}}");
lines.push(`${method} {`);
lines.push(` url: {{baseUrl}}${urlPath}`);
if (["post", "put", "patch"].includes(method) && route.body) {
lines.push(" body: json");
} else {
lines.push(" body: none");
}
if (route.auth && options.authType) {
lines.push(` auth: ${options.authType}`);
} else {
lines.push(" auth: none");
}
lines.push("}");
lines.push("");
// Auth section
if (route.auth && options.authType === "bearer") {
lines.push("auth:bearer {");
lines.push(" token: {{authToken}}");
lines.push("}");
lines.push("");
} else if (route.auth && options.authType === "basic") {
lines.push("auth:basic {");
lines.push(" username: {{username}}");
lines.push(" password: {{password}}");
lines.push("}");
lines.push("");
}
// Query params
if (route.queryParams?.length) {
lines.push("query {");
for (const param of route.queryParams) {
lines.push(` ${param.name}: ${param.value}`);
}
lines.push("}");
lines.push("");
}
// Headers
lines.push("headers {");
lines.push(" Accept: application/json");
if (["post", "put", "patch"].includes(method)) {
lines.push(" Content-Type: application/json");
}
lines.push("}");
lines.push("");
// Body
if (["post", "put", "patch"].includes(method) && route.body) {
lines.push("body:json {");
lines.push(JSON.stringify(route.body, null, 2));
lines.push("}");
lines.push("");
}
// Docs
if (route.description) {
lines.push("docs {");
lines.push(` ${route.description}`);
lines.push("}");
}
return lines.join("\n");
}
function generateEnvironments(outputDir: string, options: BrunoOptions): void {
const envsDir = path.join(outputDir, "environments");
if (!fs.existsSync(envsDir)) {
fs.mkdirSync(envsDir, { recursive: true });
}
const environments = [
{ name: "Development", baseUrl: "http://localhost:3000/api" },
{ name: "Staging", baseUrl: "https://staging-api.example.com" },
{ name: "Production", baseUrl: "https://api.example.com" },
];
for (const env of environments) {
const content = `vars {
baseUrl: ${env.baseUrl}
authToken:
}
vars:secret [
authToken
]
`;
fs.writeFileSync(path.join(envsDir, `${env.name}.bru`), content);
}
}
function generateFileName(route: RouteInfo): string {
return route.name.toLowerCase().replace(/\s+/g, "-");
}
function groupRoutesByResource(
routes: RouteInfo[]
): Record<string, RouteInfo[]> {
const groups: Record<string, RouteInfo[]> = {};
for (const route of routes) {
const parts = route.path.split("/").filter(Boolean);
const resource = parts[0] || "api";
if (!groups[resource]) {
groups[resource] = [];
}
groups[resource].push(route);
}
return groups;
}
function capitalize(str: string): string {
return str.charAt(0).toUpperCase() + str.slice(1);
}
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.
- 9d ago First seen · 675 lines · 74 tokens per session scan A 1db8b7165937
bruno-collection-generator is a skill published in the GitHub repository patricio0312rev/skillset (6 stars, last pushed 8mo ago), licensed MIT. It adds 74 tokens to every session and 3,544 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bruno-collection-generator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
prowler-test-api
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
convex-test
Generate convex-test tests for the app's Convex functions.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.