Borrowing it
Nothing to install: this file belongs to nicelight/DevRails-26. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nicelight/DevRails-26/main/AGENTS.mdgit clone --depth 1 https://github.com/nicelight/DevRails-26Wrote 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/nicelight/devrails-26/agents-md)<a href="https://agentmods.dev/instructions/nicelight/devrails-26/agents-md"><img src="https://agentmods.dev/badge/instructions/nicelight/devrails-26/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/nicelight/devrails-26/agents-md"><img src="https://agentmods.dev/badge/instructions/nicelight/devrails-26/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02914 | $0.02914 |
| Opus 5.5 | $0.01166 | $0.01166 |
| Sonnet 5.5 | $0.00583 | $0.00583 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
DevRails-26 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 1mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Что является продуктом этого репозитория
DevRails — framework агентной разработки, а не обычное приложение и не набор независимых prompts.
Canonical source через installer разворачивается в целевой проект как runtime skills, Memory Bank, workflows, protocols и validators.
Изменения оцениваются по всей цепочке:
canonical source
-> installer/generator
-> deployed target files
-> поведение runtime-агента
-> workflow state, gates и handoffs
Наличие файла в source repo не означает, что он доступен runtime-агенту в target project.
Skills как executable workflow contracts
Runtime skills, shared workflows, protocol shapes и validators являются частями одного публичного workflow contract.
Без отдельного решения нельзя менять или терять:
- inputs, outputs, statuses и verdicts;
- lifecycle и status ownership;
- blockers, stop conditions и resume routes;
- required gates и handoffs;
- task schema и registry semantics.
Leaf skill должен описывать собственный outcome и immediate handoff, а общие правила получать из доступного в target canonical reference.
Стиль runtime-инструкций
- Пиши runtime-инструкции только для исполняющего агента. Перед сохранением сокращай или объединяй формулировки и удаляй текст, если это не меняет допустимое поведение агента и workflow contract.
- Из однозначных contract-equivalent вариантов выбирай кратчайший. Не дублируй правила; rationale, пояснения и примеры оставляй только когда они нужны для однозначного исполнения.
- Каждая инструкция должна защищать workflow contract, корректность, безопасность или совместимость.
- Inputs, outputs, gates, blockers, validation и handoff формулируй нормативно.
- В остальных случаях избегай повелительного тона: внутреннюю тактику и порядок действий оставляй на выбор агента.
- Не превращай примеры, предпочтения и best practices в обязательные шаги.
- Сокращение текста не должно менять statuses, ownership, stop conditions и resume routes.
Цель и тактика
- В инструкциях, промптах и ответах фиксируй цель, ограничения и критерии результата.
- Не предписывай тактику, шаги, порядок или инструменты без основания в корректности, безопасности, совместимости или workflow contract; оставляй их выбор агенту.
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.
- 1mo ago First seen · 242 lines · 2,914 tokens per session scan A 89e36bc3bbee
DevRails-26 AGENTS.md is an instructions file published in the GitHub repository nicelight/DevRails-26 (23 stars, last pushed 1mo ago), licensed MIT. It adds 2,914 tokens to every session, about $0.0117 per session on Opus 5.5. 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.