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/masrama/nara/agents-mdgit clone --depth 1 https://github.com/MasRama/naraWrote 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/masrama/nara/agents-md)<a href="https://agentmods.dev/instructions/masrama/nara/agents-md"><img src="https://agentmods.dev/badge/instructions/masrama/nara/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 | $0.03936 | $0.03936 |
| Opus 5 | $0.01968 | $0.01968 |
| Sonnet 5 | $0.00787 | $0.00787 |
| Haiku 4.5 | $0.00394 | $0.00394 |
Grade A, and why
nara 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nara - Project Knowledge Base
Skills: Deep-dive procedures live in
.agents/skills/— load on demand.
AI Quickstart — First time here?
Read in this order (each builds on the previous):
- This file — conventions, anti-patterns, dependency policy, common pitfalls, structure. ~270 lines.
routes/web.ts— all routes in one file. API surface at a glance..agents/skills/SKILL.md— skill index. Load relevant skill when touching that pattern.docs/decisions/— ADRs explain WHY decisions were made. Read when questioning a convention.
For database schema: ls migrations/ to see table names, read the specific migration file for column types and constraints.
Then verify your work with one command:
npm run check # lint + frontend type check + layer lint + tests
Scaffold a new resource with one command:
npm run gen:resource products -- --fields="name:string,price:number"
Overview
AI-first TypeScript full-stack starter kit. Functions over classes, raw SQL over ORM, minimal abstractions.
- Backend: ultimate-express (uWebSockets.js) + better-sqlite3
- Frontend: Svelte 5 + Inertia.js + Bits UI (headless UI)
- Auth: Session-based + RBAC
- Validation: Zod
Philosophy
- No classes — functions only
- No unnecessary comments — code is self-documenting
- No abstractions — inline is fine
- Raw SQL — AI writes SQL, we just execute it
- Minimal code — less code = less bugs
Golden Principles
Opinionated, mechanical rules that keep the codebase legible for agents. Enforced by lint:layers, check:agents, check:security, or convention tests. Violations block commit.
- Functions over classes —
export const fn = () => ...orexport function fn(). Neverclass. (ADR 0002, enforced structurally) - Raw SQL over ORM — write SQL in
queries/, never use Prisma/Drizzle/Knex. (ADR 0001, dependency policy) - Descriptive handler names —
createUser,addRole,listProducts. Never genericindex/store/create/update/destroy. (ADR 0009, L11-L12) - Layer boundaries are hard — handlers → queries → services → core. Import direction enforced. Queries never import handlers. Validators never import services. (L14-L17)
- Two response types, never mixed — page routes return
res.inertia(), data routes returnjsonSuccess()/jsonError(). (L3-L4) api()wrapper for all frontend HTTP — never rawfetch()oraxiosin components, neverrouter.post/put/patch/delete. (L5-L7)- Svelte 5 runes only —
$state,$derived,$effect,$props. NeveronMount,$:,export let, or Svelte stores. (L8) - Logger, not console —
Logger.info/warn/error.console.logonly in bootstrap files where Logger isn't initialized. (L9) hashPassword()from Authenticate, never bcrypt direct — the wrapper enforces the correct cost factor. (L10)- English for all user-facing messages — error messages, toast, validation. (ADR 0010)
- AGENTS.md stays in sync with code — every documented directory has an AGENTS.md, every Structure table matches the actual files. (check:agents, convention test)
- Files stay small — source files under 500 lines. Split before they grow into monsters. (check:filesize)
- Docs links resolve — no broken markdown links in AGENTS.md, skills, or ADRs. (check:links)
- No new
any— type safety is non-negotiable. Existinganyis baselined; newanyblocks CI. Use proper types. (check:types)
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 · 281 lines · 3,936 tokens per session scan A e797ddd43346
nara AGENTS.md is an instructions file published in the GitHub repository MasRama/nara (5 stars, last pushed 7d ago), licensed MIT. It adds 3,936 tokens to every session, about $0.0197 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.