Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nazmulnahid-git/Ai-Stacknpx agentmods add skills/nazmulnahid-git/ai-stack/adonis-next-monorepoWrote 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/nazmulnahid-git/ai-stack/adonis-next-monorepo)<a href="https://agentmods.dev/skills/nazmulnahid-git/ai-stack/adonis-next-monorepo"><img src="https://agentmods.dev/badge/skills/nazmulnahid-git/ai-stack/adonis-next-monorepo/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/nazmulnahid-git/ai-stack/adonis-next-monorepo"><img src="https://agentmods.dev/badge/skills/nazmulnahid-git/ai-stack/adonis-next-monorepo.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 | $0.00103 | $0.01485 |
| Opus 5.5 | $0.00041 | $0.00594 |
| Sonnet 5.5 | $0.00021 | $0.00297 |
| Haiku 4.5 | $0.00010 | $0.00148 |
Grade A, and why
adonis-next-monorepo 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
adonis-next-monorepo
Creates a working monorepo from template/, a snapshot of a project whose setup was verified end to end. The result is identical in structure, tooling and configuration; only the name and description change. The template's own docs/conventions.md records every convention and why it exists, so read that when the user asks why something is set up the way it is, or wants to change it.
What it creates
- Workspaces:
apps/api(AdonisJS 7, Lucid/Postgres, VineJS, token + session auth, Tuyau),apps/web(Next.js 16 App Router, React 19, Tailwind 4, TanStack Query),packages/ui(shadcn on Base UI),packages/eslint-config,packages/typescript-config. - API structure: feature modules in
app/modules/<name>/<name>.{routes,controller,service,validator}.ts, generated bynode ace make:module <name>. Starts withauthandhealth. Every response is{ data }or{ errors: [...] }, and routes require auth unless marked public. - Web structure:
useQuery(api.<module>.<action>.queryOptions())rendered through<QueryState>, plus mutation error toasts and env validated with zod. - Tooling: strict TypeScript 6.0, one ESLint config with custom structure rules, Prettier, Husky + lint-staged + commitlint, branch-name and migration guards, a GitHub Actions CI workflow, Dependabot, VS Code settings, and AI rules in
AGENTS.md.
Steps
1. Collect the inputs
You need:
- Name: kebab-case, e.g.
acmeormy-app. It becomes the@<name>/*package scope; the Postgres user and databases use the snake_case form. - Title: the display name. Defaults to the name in Title Case.
- Description: one line, used in the README and on the home page.
- Target directory: must be new or empty.
Ask for any missing input in one message. Then confirm the tools exist: node -v (24+), pnpm -v, git --version, and docker info (the Docker daemon must be running; start Docker Desktop if it isn't).
Done when all four inputs are known and every tool responds.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/create.mjs 2.9 KB runs code
- template/_gitignore 430 B
- template/.editorconfig 336 B
- template/.github/dependabot.yml 682 B
- template/.github/pull_request_template.md 586 B
- template/.github/workflows/ci.yml 3.0 KB
- template/.husky/commit-msg 33 B
- template/.husky/pre-commit 75 B
- template/.husky/pre-push 35 B
- template/.prettierignore 154 B
- template/.prettierrc 257 B
- template/.vscode/extensions.json 198 B
- template/.vscode/settings.json 696 B
- template/AGENTS.md 2.4 KB
- template/apps/api/.env.example 478 B
- template/apps/api/.env.test 54 B
- template/apps/api/ace.js 802 B runs code
- template/apps/api/adonisrc.ts 3.4 KB runs code
- template/apps/api/app/exceptions/handler.ts 2.3 KB runs code
- template/apps/api/app/middleware/auth_middleware.ts 521 B runs code
- template/apps/api/app/middleware/container_bindings_middleware.ts 619 B runs code
- template/apps/api/app/middleware/force_json_response_middleware.ts 290 B runs code
- template/apps/api/app/middleware/public_middleware.ts 427 B runs code
- template/apps/api/app/middleware/silent_auth_middleware.ts 453 B runs code
- template/apps/api/app/models/user.ts 741 B runs code
- template/apps/api/app/modules/auth/auth.controller.ts 1.2 KB runs code
- template/apps/api/app/modules/auth/auth.routes.ts 827 B runs code
- template/apps/api/app/modules/auth/auth.service.ts 964 B runs code
- template/apps/api/app/modules/auth/auth.validator.ts 475 B runs code
- template/apps/api/app/modules/health/health.controller.ts 452 B runs code
- template/apps/api/app/modules/health/health.routes.ts 488 B runs code
- template/apps/api/app/modules/health/health.service.ts 645 B runs code
- template/apps/api/app/transformers/user_transformer.ts 337 B runs code
- template/apps/api/bin/console.ts 1.3 KB runs code
- template/apps/api/bin/server.ts 1.3 KB runs code
- template/apps/api/bin/test.ts 1.7 KB runs code
- template/apps/api/commands/make_module.ts 4.9 KB runs code
- template/apps/api/config/app.ts 2.1 KB runs code
- template/apps/api/config/auth.ts 1.3 KB runs code
- template/apps/api/config/bodyparser.ts 1.7 KB runs code
- template/apps/api/config/cors.ts 1.3 KB runs code
- template/apps/api/config/database.ts 1.1 KB runs code
- template/apps/api/config/encryption.ts 785 B runs code
- template/apps/api/config/hash.ts 2.2 KB runs code
- template/apps/api/config/logger.ts 1.2 KB runs code
- template/apps/api/config/session.ts 1.6 KB runs code
- template/apps/api/config/shield.ts 1.8 KB runs code
- template/apps/api/database/factories/user_factory.ts 285 B runs code
- template/apps/api/database/migrations/1761885935168_create_users_table.ts 562 B runs code
- template/apps/api/database/migrations/1768620764696_create_access_tokens_table.ts 821 B runs code
- template/apps/api/database/schema_rules.ts 115 B runs code
- template/apps/api/database/schema.ts 1.5 KB runs code
- template/apps/api/eslint.config.js 100 B runs code
- template/apps/api/package.json 2.1 KB
- template/apps/api/providers/api_provider.ts 2.8 KB runs code
- template/apps/api/start/env.ts 1.1 KB runs code
- template/apps/api/start/kernel.ts 1.6 KB runs code
- template/apps/api/start/routes.ts 565 B runs code
- template/apps/api/start/validator.ts 719 B runs code
- template/apps/api/stubs/make/module/controller.stub 772 B
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 · 104 lines · 103 tokens per session scan A 8d0a735cd9f3
adonis-next-monorepo is a skill published in the GitHub repository nazmulnahid-git/Ai-Stack (4 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 1,485 once invoked, about $0.0004 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 2026-10-27.
Other skills, from other repositories
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
nornweave-api
Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…
apiclaw
Set up APIClaw and land one live API execute. When a user says "set up https://apiclaw.cloud/SKILL.md", or you need a research API call without collecting provider keys, follow this file. Auth is Clerk via npx @nordsym/apiclaw auth login. Confirm with npx @nordsym/apiclaw auth whoami before any execute. Execution is…
auth-middleware
Generates authentication and authorization middleware for Express/Fastify/Hono.