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/edvardgrishin27/nativeprompt/agents-mdgit clone --depth 1 https://github.com/edvardgrishin27/nativepromptWrote 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/edvardgrishin27/nativeprompt/agents-md)<a href="https://agentmods.dev/instructions/edvardgrishin27/nativeprompt/agents-md"><img src="https://agentmods.dev/badge/instructions/edvardgrishin27/nativeprompt/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 | $0.00652 | $0.00652 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
nativeprompt 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.
What it actually says
AGENTS.md — инструкции для Codex
Ты работаешь в репозитории nativeprompt — CLI-инструмент, который переписывает промпт под официальные правила текущей модели (Claude Code / Codex) и объясняет почему. Обзор — в README.md, честные границы — в CLAIMS.md.
ГРАНИЦА (важно)
Эти части — авторские и СТАБИЛЬНЫЕ, НЕ редактируй их напрямую:
nativeprompt/(весь Python-пакет, включаяrules/*.json)tests/,examples/SKILL.md,README.md,CLAIMS.md,pyproject.toml,.github/
Твоя рабочая папка — только codex/. Всё, что ты создаёшь или меняешь, кладёшь туда. Изменения в core предлагай как патчи/заметки внутри codex/, НЕ применяй к файлам выше.
ТВОЯ ЗАДАЧА
- Изучи и проверь. Установи (
pip install -e .), прогониpython -m pytest -q, попробуй:python -m nativeprompt improve "почини баг, думай пошагово, перепроверь себя" --model gpt-5.6и--model claude-opus-5. Убедись, что контраст правок работает. - Сделай Codex-нативную интеграцию в
codex/integration/. У Claude Code уже естьSKILL.md; у Codex — своя конвенция. Добавь то, что нативно для Codex: например, готовый фрагментAGENTS.mdдля пользователя, который заставит Codex вызыватьnativeprompt improveпри просьбе «улучши промпт», и/или обёртку под твой формат кастомных промптов/инструментов. Следуй актуальным правилам Codex (developers.openai.com/codex). - Ревью. В
codex/REVIEW.md— конкретные предложения по улучшению (баги, эвристикиanalyze.py, покрытие правил, UX CLI). Патчи к core — файлами вcodex/patches/(unified diff), НЕ применяя их.
ПРАВИЛА КАЧЕСТВА
- Правила в шпаргалке привязаны к ОФИЦИАЛЬНЫМ докам вендоров (
source-URL). Ничего не выдумывай — если предлагаешь новое правило, дай ссылку на первоисточник. - Инструмент НЕ додумывает задачу за пользователя (недостающее — плейсхолдеры
‹…›). Сохраняй этот принцип. - Ядро — zero-deps (stdlib). Не тащи зависимости в core.
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 · 24 lines · 652 tokens per session scan A ae772d70186d
nativeprompt AGENTS.md is an instructions file published in the GitHub repository edvardgrishin27/nativeprompt (116 stars, last pushed today), licensed MIT. It adds 652 tokens to every session, about $0.0033 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.