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/evandersondev/darto/agents-mdgit clone --depth 1 https://github.com/evandersondev/dartoWhat 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 | $0.01905 | $0.01905 |
| Opus 5 | $0.00953 | $0.00953 |
| Sonnet 5 | $0.00381 | $0.00381 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
darto 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 2d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository. For end-user API docs
see darto/REFERENCE.md and https://darto-docs.vercel.app/.
For task-scoped procedures (add a route, validate a request, write
middleware, scaffold a project), load the matching Claude Skill in
skills/. Machine-readable docs for the site live at
/llms.txt.
Overview
Darto is a minimal, type-safe web framework for pure Dart (no Flutter, no
Node/JS). It is inspired by Express but its actual programming model is
Hono-style: everything flows through a single Context object. This repo is
a monorepo — the core darto package plus an ecosystem of plugins
(darto_*) and runnable examples/.
The #1 thing to get right: Context, not (req, res, next)
Darto's lineage is Express, but as of v1.x the API is not Express. Do not
write (Request req, Response res, Next next) handlers, res.send(), or
Express-style error middleware — that is the old API and will not compile.
A handler takes a single Context c and returns a Response:
import 'package:darto/darto.dart';
void main() {
final app = Darto();
app.get('/users/:id', [], (Context c) {
final id = c.req.param('id'); // read request via c.req
return c.ok({'id': id}); // RETURN a response helper
});
app.listen(3000);
}
The three typedefs that define the whole framework:
typedef Handler = FutureOr<Response>? Function(Context c);
typedef Middleware = FutureOr<void> Function(Context c, Next next);
typedef Next = Future<void> Function();
Conventions an agent won't infer
- Middleware list is a required positional arg on every verb method. Pass
[]when there is no route-level middleware:app.get(path, [middlewares], handler). Never omit it. - Return responses, don't "send" them. Use the helpers and
returnthem:c.ok,c.created,c.noContent,c.badRequest,c.unauthorized,c.forbidden,c.notFound,c.conflict,c.internalError, or typedc.json(data, [status]),c.text,c.html,c.redirect,c.binary,await c.file(...),await c.download(...). Chain status withc.status(206).json(...). c.body(...)is a response helper (raw body), not a request reader.- Read the request through
c.req:c.req.param('id')/paramInt,c.req.query('page')/queryInt/queryBool,c.req.header('...'), and the body viaawait c.req.json()(orc.req.json<T>(T.fromJson)),c.req.text(),c.req.blob(). - Per-request state:
c.set('k', v)/c.get<T>('k'); auth shortcutc.user. - Writing middleware: factory returning a closure;
await next()to continue,return(withoutnext) to short-circuit:Middleware requireAdmin() => (Context c, Next next) async { if (c.user?['role'] != 'admin') { c.forbidden(); return; } await next(); }; - Error & 404 handling use Context too — not Express error middleware:
app.onError((DartoError err, Context c) => c.internalError({'error': err.message})); app.notFound((Context c) => c.notFound({'error': 'not found'})); - Validation is
zValidatorfromdarto_validator(Zod-style viazard), used as route middleware; read the result withc.req.valid<Map<String, dynamic>>('json' | 'query' | 'param'). - There is no built-in ORM/database layer. Don't introduce or assume one (e.g. "Dartonic") — persistence is left to the application.
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.
- 2d ago First seen · 162 lines · 1,905 tokens per session scan A 5809d6196813
darto AGENTS.md is an instructions file published in the GitHub repository evandersondev/darto (43 stars, last pushed 1mo ago), licensed MIT. It adds 1,905 tokens to every session, about $0.0095 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
igniter-js GEMINI.md
Gemini CLI instructions for felipebarcelospro/igniter-js, covering 1. identity and profile, 2. about the igniter.js monorepo, 3. personality and communication, 4. lia's core responsibilities (the 4 pillars) and 5. technical guidelines and methodology.
igniter-js AGENTS.md
AGENTS.md instructions for felipebarcelospro/igniter-js, covering lia - ai agent for igniter.js, 1. identity & mission, core mission, key responsibilities and 2. project overview.
igniter-js writing-style.instructions.md
Instructions for felipebarcelospro/igniter-js, covering ✍️ unified documentation style guide (for llms & authors), 🎯 core style principles (applies to all documentation), 📘 documentation (docs): writing style, installation and quick start.
igniter-js writing-guidelines.instructions.md
Instructions for felipebarcelospro/igniter-js, covering writing guidelines for humans and llms, core style principles, fumadocs-specific guidelines, available mdx components and component usage examples.
wa-automate-nodejs AGENTS.md
AGENTS.md instructions for open-wa/wa-automate-nodejs, covering repository instructions, commit policy, no ai attribution, commit grouping and gitmoji reference.
keryx CLAUDE.md
Instructions for actionhero/keryx, covering claude.md, project overview, monorepo structure, development environment and environment setup.