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 instructions/filipebraida/adonisjs-starter-kit/agents-mdgit clone --depth 1 https://github.com/filipebraida/adonisjs-starter-kitWrote 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/instructions/filipebraida/adonisjs-starter-kit/agents-md)<a href="https://agentmods.dev/instructions/filipebraida/adonisjs-starter-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/filipebraida/adonisjs-starter-kit/agents-md.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 | $0.01722 | $0.01722 |
| Opus 5 | $0.00861 | $0.00861 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
adonisjs-starter-kit AGENTS.md 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Meta-rule
ALWAYS look for the existing pattern before writing anything new. This repo is highly consistent; new code should mirror the closest existing example, not invent shape. Search first, code second.
Scope
- Minimal diff. Prefer the smallest change that satisfies the request — don't refactor unrelated code, rename identifiers "on the way", or restructure imports beyond the diff.
- If the task drifts, ask before expanding scope.
Stack
AdonisJS 7 (session auth + Bouncer + Lucid), Inertia + React 19, Tailwind 4 + shadcn/Radix, Postgres 16, pnpm monorepo (Turbo).
Commands
pnpm dev— dev serverpnpm test— full suitepnpm typecheck && pnpm lint— before saying "done"pnpm infra:up— Postgres + Mailpit via composepnpm ace <cmd>— Adonis CLI from the repo root (shortcut forpnpm --filter web exec node ace <cmd>)pnpm ace make:module <name> [--db] [--i18n] [--events]— scaffold a module and wire every touchpoint (alias, preload, migration path, tsconfig include, i18n loader)
Done criteria
Before reporting completion:
- Run
pnpm typecheck && pnpm lint. - Run the narrowest relevant test first (module functional spec) before falling back to
pnpm test. - If a required command failed to run (missing infra, no network, etc.), stop and report the failure with the relevant output — do not claim completion.
Architecture — module per bounded context
Every bounded context lives at app/<mod>/ as a self-contained module. A module owns the ubiquitous language of one context and may hold multiple aggregates inside — modules are not 1:1 with aggregates. Existing modules: auth, users, marketing, analytics, common, core, notifications. Each module dir is aliased as #<mod>/* in apps/web/package.json → "imports" — see the module-scaffolding skill to add one.
app/<module>/
actions/ # single-purpose class with .handle(input)
controllers/ # thin: validate → action → redirect/render
queries/ # read-only Lucid query classes
policies/ # extend BasePolicy, one per resource
models/, mixins/, services/, exceptions/, enums/
middleware/ # singular — HTTP middleware (registered in start/kernel.ts)
transformers/
validators/ # one file per entity — validators/users.ts, validators/tokens.ts
database/{factories,migrations,seeders}/
resources/lang/ # i18n JSON, per module per locale
ui/ # Inertia pages + React components
mails/ # BaseMail classes — *_notification.ts (see the mail skill)
notifications/ # Notification classes (if the module emits)
types/events.ts # EventsList declaration merge (if the module emits)
start/{events,view}.ts
routes.ts
tests/{unit,functional}/
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 · 121 lines · 1,722 tokens per session scan A 65ac22a634f2
adonisjs-starter-kit AGENTS.md is an instructions file published in the GitHub repository filipebraida/adonisjs-starter-kit (94 stars, last pushed 25d ago), licensed MIT. It adds 1,722 tokens to every session, about $0.0086 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 instructions, from other repositories
coss AGENTS.md
AGENTS.md instructions for cosscom/coss, covering agents.md and main documentation.
ui-beats AGENTS.md
Instructions for nikhils4/ui-beats: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before…
voicetypr AGENTS.md
AGENTS.md instructions for moinulmoin/voicetypr, covering voicetypr, core commands, development, quality checks (run before commits) and build.
voicetypr CLAUDE.md
Claude Code instructions for moinulmoin/voicetypr, covering claude.md, project overview, development guidelines, development commands and architecture.
friendshipdaycare copilot-instructions.md
Copilot instructions for williamjxj/friendshipdaycare, covering copilot instructions: friendship corner daycare website, project overview, key technologies, ui/ux & animation conventions and image & asset optimization.
friendshipdaycare AGENTS.md
AGENTS.md instructions for williamjxj/friendshipdaycare, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.