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/47vigen/raqam/agents-mdgit clone --depth 1 https://github.com/47vigen/raqamWhat 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 | $0.01214 | $0.01214 |
| Opus 5 | $0.00607 | $0.00607 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
raqam 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Conventions for coding agents working in this repository.
Just want to use raqam in another project? You don't need this file. Read
skills/raqam/SKILL.md, or point your agent at https://raqam.47vigen.com/llms.txt (index) or https://raqam.47vigen.com/llms-full.txt (every page, one file). The shipped.d.tsfiles carry JSDoc with runnable examples, so hoveringNumberFieldin an editor is often enough.
What this is
raqam — a headless React number input with live, cursor-stable formatting and
i18n digit support. Published to npm, MIT, zero runtime dependencies. React
18/19 are peer deps. pnpm 10.
Two different Node floors, don't conflate them: the published package
supports Node ≥20.9 (engines.node), while developing on this repo needs
Node 22+ — jsdom@30, the vitest environment, requires
^22.22.2 || ^24.15.0 || >=26.0.0. .nvmrc pins 22 and CI reads it.
Layout
| Path | What lives there |
|---|---|
src/core/ |
No React. Formatter, parser, cursor math, digit normalizer, presets. Ships as raqam/core and raqam/server. |
src/react/ |
Hooks and the NumberField compound components. Ships as raqam/react. |
src/locales/ |
Side-effect digit plugins (fa, ar, bn, hi, th). |
src/stories/ |
Storybook, snapshotted by Chromatic. |
e2e/ |
Playwright component tests — real browsers, for caret and RTL behaviour. |
docs/ |
The Next.js + Fumadocs site. Separate workspace package, not published. |
skills/raqam/ |
The installable agent skill. Keep in sync with the API. |
DEFINITION.md |
Historical design spec written before implementation. Rationale, not API docs — do not treat it as current. |
Verifying your work
pnpm lint is read-only (biome check src/); pnpm lint:fix writes. Never
use a writing command as a gate.
pnpm typecheck # tsc --noEmit
pnpm test # vitest run
pnpm lint # biome check src/
pnpm build # tsup — must succeed before publint/size
pnpm publint # export map validity
pnpm size # size-limit budgets, enforced in CI
pnpm test:e2e # Playwright CT — needs `pnpm exec playwright install` once
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 · 92 lines · 1,214 tokens per session scan A 97288845d13e
raqam AGENTS.md is an instructions file published in the GitHub repository 47vigen/raqam (22 stars, last pushed 9d ago), licensed MIT. It adds 1,214 tokens to every session, about $0.0061 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
formkind AGENTS.md
Instructions for khanhcamap2020-sudo/formkind, covering agent guide, commands and change rules.
pricegrab AGENTS.md
Instructions for mablanco/pricegrab, covering agents.md, authoritative sources (read these first), workflow (spec-driven development), non-negotiable operating rules and project layout (current).
supabase studio-composition-patterns.instructions.md
Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).
recharts AGENTS.md
Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
react-seed AGENTS.md
Instructions for guokaigdg/react-seed, covering agents.md, 目录, 1. 项目概览, 2. 技术栈 and 3. 目录结构.