agentmods.dev

FMT-exocortex-template: Instructions file for Claude Code

CLAUDE.md

FMT-exocortex-template CLAUDE.md is an instructions file for Claude Code from TserenTserenov/FMT-exocortex-template. It costs 4,950 tokens per session, scanned A, original, MIT.

A set of instructions for working across repositories that use a layered architecture and a defined opening, working, and closing process.

In plain words
What is it for?
Use it to guide repository setup, creation of domain-specific knowledge packs, and agent work that follows the project's documented protocols.
Why use it?
It gives coding agents rules for where domain knowledge comes from, how repositories relate to one another, and which steps must not be skipped. The excerpt does not fully describe every instruction.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is TserenTserenov/FMT-exocortex-template's own configuration. It tells Claude Code how to work on FMT-exocortex-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything FMT-exocortex-template configures →

not rated 50repo +1 changed yesterday A scan 4,950 tokens original MIT
View source ↗ TserenTserenov/FMT-exocortex-template
Reuse

Borrowing it

Nothing to install: this file belongs to TserenTserenov/FMT-exocortex-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TserenTserenov/FMT-exocortex-template/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-template

Made for: Claude Code.

Wrote 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.

agentmods badge for FMT-exocortex-template CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tserentserenov/fmt-exocortex-template/claude-md/github.svg)](https://agentmods.dev/instructions/tserentserenov/fmt-exocortex-template/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tserentserenov/fmt-exocortex-template/claude-md"><img src="https://agentmods.dev/badge/instructions/tserentserenov/fmt-exocortex-template/claude-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.

agentmods 80×15 button for FMT-exocortex-template CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tserentserenov/fmt-exocortex-template/claude-md"><img src="https://agentmods.dev/badge/instructions/tserentserenov/fmt-exocortex-template/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,950 This file is loaded in full into every session.
When invoked 4,950 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04950 $0.04950
Opus 5 $0.02475 $0.02475
Sonnet 5 $0.00990 $0.00990
Haiku 4.5 $0.00495 $0.00495

Measured yesterday against content hash 9911196ea6c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

FMT-exocortex-template 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 yesterday.

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.

CLAUDE.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Инструкции для всех репозиториев

Kimi → AGENTS.md, Hermes → Aisystant MCP get_instructions; доставка ядра из авторского IWE в этот шаблон — внутренний авторский конвейер (не входит в шаблон, недоступен пользователю). Slim-ядро: триггеры + правила hot; детали → memory/, .claude/rules-lazy/, .claude/skills/.

1. Архитектура репозиториев

Base (ZP, FPF, SPF, FMT-*) = принципы + форматы, первоисточник платформы · Pack = паспорт предметной области, первоисточник пользователя · DS (instrument/governance/surface) = код, планы, курсы — производное от Pack.

Fallback Chain (где SoT): DS → Pack → Base (SPF → FPF → ZP). Pack = source-of-truth для доменного знания; DS меняется вслед за Pack. Лестница принципов: ZPF → FPF → SPF → TPF → LPF — полная таблица уровней → memory/repo-type-rules.md; словарь ailev ↔ IWE → memory/fpf-reference.md.

Pack Creation Gate: хочешь создать Pack → /pack-new (структура SPF/pack-template/, процесс SPF/process/01-11, FPF/SPF клонируются автоматически). Имя = существительное-домен (не тема, не инструмент).

2. ОРЗ-фрактал (Открытие → Работа → Закрытие)

Пропуск Открытия = незапланированная работа. Пропуск Закрытия = незафиксированный результат. Сессия: memory/protocol-open.md § Сессия → memory/protocol-work.md → /run-protocol close · День: /day-open («открывай») → /run-protocol day-close · Неделя: /run-protocol week-close · Месяц: /month-close (первый Пн, до Strategy Session).

Блокирующие правила

SoT (WP-272 Ф1): PACK-agent-rules/rules/AR.NNN.md (реестр .claude/rules-registry.yaml) — авторский источник, не шипится в шаблон (генератор .claude/scripts/generate-rules-registry.py требует PACK-agent-rules, которого у пользователя нет). На пользовательской установке — шипящаяся выжимка тех же 10 правил → .claude/rules-lazy/blocking-rules-full.md. Приоритет = нумерация: структурное (1-5) перевешивает поведенческое (6-10).

  1. WP Gate: ЛЮБОЕ задание → memory/protocol-open.md ДО начала работы. Новый РП → Ритуал согласования → явное «да»/«делаем»/«открывай»; без этого не регистрировать.
  2. Push: «заливай»/«запуши»/«закрывай» → commit + push без вопросов, ДО отчёта Закрытия. Любой Close: git status --short по всем репо → незафиксированное commit + push ДО следующего шага.
  3. Close: Триггер Закрытия → протокол Закрытия → выполнить.
  4. Pull-on-Touch: PreToolUse-хук автоматически делает best-effort git pull --rebase --autostash один раз на репо. Не выполняй ручной cd && git pull; при сбое хук сообщает potentially stale, процедура → memory/reference/agent-core.md.
  5. Чеклист-верификация: Quick/Day Close — sub-agent Haiku R23 сверяет с чеклистом. Исключения: ≤15 мин или без изменений файлов.
  6. Hooks/Scripts Bypass Gate (S-33): без явного разрешения не менять .claude/hooks|scripts/, .iwe-runtime/, FMT-exocortex-template/, не обходить хуки; блок хука → bug-файл + пилоту + ждать. → .claude/rules-lazy/hooks-bypass-gate.md.
  7. Автономность: не спрашивать подтверждения — выполни → отчитайся. Исключения: необратимо-разрушительное; WP Gate Ритуал; choice-question. Полный текст → .claude/rules-lazy/blocking-rules-full.md п.7.
  8. Напоминания (S-44): «напомни через X» → send_telegram_message(schedule_at) + ScheduleWakeup резерв; резерв сработал → сначала Telegram, потом чат.
  9. Финиш > отлог (S-46): доп. задача → дефолт «делаю сейчас»; «сейчас или потом?» = анти-паттерн. Исключения и приоритет WP Gate → .claude/rules-lazy/blocking-rules-full.md п.9.

Read the full file on GitHub · 186 lines

Changes

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.

  1. yesterday Changed · +2 lines · +150 tokens per session 9911196ea6c7
  2. 9d ago First seen · 184 lines · 4,800 tokens per session scan A 7051cbfb4b12

Subscribe to this mod's changes

FMT-exocortex-template CLAUDE.md is an instructions file published in the GitHub repository TserenTserenov/FMT-exocortex-template (50 stars, last pushed today), licensed MIT. It adds 4,950 tokens to every session, about $0.0248 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.

Claude Codeagentic-workflowsai-agentsai-second-brainanthropic-claudeclaude-plugin
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens