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/begoon/rapira/claude-mdgit clone --depth 1 https://github.com/begoon/rapiraWrote 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/begoon/rapira/claude-md)<a href="https://agentmods.dev/instructions/begoon/rapira/claude-md"><img src="https://agentmods.dev/badge/instructions/begoon/rapira/claude-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 | $0.02562 | $0.02562 |
| Opus 5 | $0.01281 | $0.01281 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade A, and why
rapira CLAUDE.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 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — working on this codebase
Project-level notes for future Claude sessions. The TL;DR: this is a faithful interpreter for the 1985 Agat dialect of Rapira (not the modern Rapture dialect). When in doubt about language semantics, the source of truth order is:
RAPIRA.md— the canonical 1985 spec, in RussianSPEC.md— what this implementation actually does, including documented deviations- The code
Stack
- Bun for the runtime, test runner, and bundler. No Node, no Vite, no Svelte, no SvelteKit. They were ripped out — don't add them back without a strong reason.
- TypeScript with
allowImportingTsExtensionsso.tsextensions appear in imports (import './foo.ts'). The web tsconfig (web/tsconfig.json) inherits the same convention. - CodeMirror 6 in the playground; the rest of the playground is plain DOM.
justis optional — every recipe inJustfileis a thin wrapper around abun runinvocation.
Commands
| What | Command |
|---|---|
| Tests | bun test |
| Type-check | bun run typecheck |
Run a .rap file |
bun run cli/index.ts FILE.rap |
| Render turtle output | bun run cli/index.ts FILE.rap --svg out.svg |
| Web dev server | bun run dev (port 10000) |
| Web production build | bun run build → docs/ (GitHub Pages-ready) |
| Bundle CLI for npm | bun run cli:build → dist/rapira.js |
| Preview npm tarball | npm pack --dry-run (or just pack) |
Layout
src/ interpreter core — pure, no I/O dependencies
lexer.ts tokeniser; Russian-only keyword table normalised to ru-RU upper-case
parser.ts recursive descent → AST
ast.ts AST node types
interpreter.ts tree-walker; defines Host interface, BufferedHost
values.ts RValue + deep equality + arithmetic dispatch + display
environment.ts scope chain
errors.ts Pos + RapiraError subclasses
graphics.ts GfxEvent typed union + sinks
fs.ts FileSystem capability + InMemoryFileSystem
stdlib/gfx.ts documented Agat graphics primitives + Чертёжник turtle
keywords.ts bilingual lookup table (Russian-only — "bilingual" is a misnomer left over from earlier; do not add English keywords)
cli/ Node-backed host: stdin/stdout, NodeFileSystem, SVG renderer
Bundled by scripts/cli-build.ts into dist/rapira.js
for npm publish (`npx rapira FILE.rap`)
web/ vanilla DOM + CodeMirror 6 playground
worker.ts interpreter in a Web Worker (sync sleep via Atomics.wait)
lib/ renderer.ts (canvas), rapira-mode.ts (CodeMirror language + light/dark highlight)
scripts/web-build.ts Bun-only build driver (replaces Vite). Also copies tests/snippets/ → docs/examples/
tests/
snippets/ *.rap + *.expected.txt / *.expected.svg — runner walks the directory
*.test.ts unit tests grouped by layer
examples/ .rap files for the CLI; not the same as tests/snippets/
RAPIRA.md the 1985 spec
SPEC.md this implementation's contract
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 · 162 lines · 2,562 tokens per session scan A a139193acaee
rapira CLAUDE.md is an instructions file published in the GitHub repository begoon/rapira (56 stars, last pushed 3mo ago), licensed MIT. It adds 2,562 tokens to every session, about $0.0128 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
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.