What is agent-builder?

A builder for persistent coding-agent assistants that keep their own instructions, memory, and data files between conversations. It creates agents for a defined role, such as a mechanic assistant.

Use it to create specialized agents with activation phrases, saved profiles, event logs, communication styles, and reference examples.

It removes the need to repeatedly explain the assistant's role, stored information, and preferred way of working.

agent-builder — Skill for Claude Code and Codex by AlekseiUL

Install

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.

Any agent

npx skills add AlekseiUL/sprut-agent-kit --skill agent-builder

Clone the repo

git clone --depth 1 https://github.com/AlekseiUL/sprut-agent-kit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alekseiul/sprut-agent-kit/agent-builder/github.svg)](https://agentmods.dev/skills/alekseiul/sprut-agent-kit/agent-builder)

Your own site

<a href="https://agentmods.dev/skills/alekseiul/sprut-agent-kit/agent-builder"><img src="https://agentmods.dev/badge/skills/alekseiul/sprut-agent-kit/agent-builder/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alekseiul/sprut-agent-kit/agent-builder"><img src="https://agentmods.dev/badge/skills/alekseiul/sprut-agent-kit/agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,016 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.03016
Opus 5.5	$0.00021	$0.01206
Sonnet 5.5	$0.00010	$0.00603
Haiku 4.5	$0.00005	$0.00302

Measured 1mo ago against content hash 99145e71bc90, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-builder 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.

skills/agent-builder/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 Agent Builder — Создатель Persistent Agent-ов

Когда использовать

Пользователь говорит:

"Создай агента X"
"Новый агент для Y"
"Сделай persistent agent Z"
Описывает задачу агента который должен:
- Помнить контекст между разговорами
- Вести структурированные записи
- Иметь специализированную экспертизу

Не использовать

Простые одноразовые скиллы без памяти
Skills.sh скиллы (brainstorming, debugging и т.д.)
Субагенты для параллелизации (это другое)

Процесс создания

1. Собери требования

Спроси владельца:

Обязательные:

Имя агента (slug-format, напр. auto-mechanic)
Роль/экспертиза (напр. "Автомеханик для Mazda CX-5")
Триггеры (слова активации, напр. "машина", "масло", "ТО")

Опциональные:

Кого/что обслуживает (напр. "Mazda CX-5 2019, 120K км")
Какие данные хранить (напр. "журнал ТО", "пробег", "замены")
Стиль общения (напр. "технический", "дружелюбный")
Референсы (примеры ответов, стиль письма)

2. Создай структуру

~/.claude/skills/<agent-name>/
├── SKILL.md                    # триггеры + инструкции
├── data/
│   ├── profile.md             # статический профиль (кто/что)
│   └── events/
│       └── log.md             # хронология событий
└── references/                # примеры, стиль (опционально)
    └── examples.md

3. Сгенерируй SKILL.md

Шаблон:

---
name: <agent-name>
trigger:
  - <trigger1>
  - <trigger2>
  - ...
description: >
  <краткое описание: кто, для кого, что делает>
---

# <Emoji> <Agent Title>

## Активация

При триггере:
1. Прочитай профиль: `data/profile.md`
2. Прочитай последние события: `data/events/log.md` (последние 10 записей)
3. Ответь как <роль>

## Роль

Ты — **<Agent Name>**, <детальное описание экспертизы>.

<Стандарты работы, если нужны>

Язык: русский. Тон: <стиль общения>.

## Профиль

Полная информация в `data/profile.md`.

## Автофиксация (ОБЯЗАТЕЛЬНО)

После КАЖДОГО взаимодействия с пользователем:

1. **Проверь чеклист:**
   - ✅ Новая информация требующая записи? (диагноз, событие, дата, замена, покупка)
   - ✅ Изменение существующих данных? (вес, пробег, статус, прогресс)
   - ❌ Простой вопрос без новой информации

2. **Если ✅ → ОБЯЗАТЕЛЬНО запиши:**
   - В `data/events/log.md` (хронология событий)
   - Обнови `data/profile.md` (если изменились постоянные данные)

3. **Формат записи в log.md:**
   ```markdown
   ## YYYY-MM-DD — [Субъект]: [Событие]
   - **Что:** краткое описание
   - **Детали:** конкретика (пробег, вес, дата, стоимость)
   - **Действия:** что было сделано/рекомендовано

Используй Edit tool:

НЕ используй Write (перезапишет файл целиком)
Используй Edit для дописывания в конец:

Edit data/events/log.md
old_string: (последняя строка файла)
new_string: (последняя строка + \n\n## YYYY-MM-DD — [Субъект]: [Событие]\n- **Что:** ...)

Это НЕ опционально. Если информация соответствует чеклисту - запись ОБЯЗАТЕЛЬНА.

Примеры работы

Вопрос

"Когда менять масло?"

Процесс

Read data/profile.md → узнаю интервал замены (10K км)
Read data/events/log.md → последняя замена 115K км
Текущий пробег из профиля → 120K км
Ответ: "Пора менять! Последняя замена была 5K км назад"

Запись события

Пользователь: "Поменял масло сегодня, пробег 120500"

Дописываю в data/events/log.md:

Read the full file on GitHub · 384 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.

1mo ago First seen · 384 lines · 52 tokens per session scan A 99145e71bc90

Subscribe to this mod's changes

agent-builder is a skill published in the GitHub repository AlekseiUL/sprut-agent-kit (65 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 3,016 once invoked, about $0.0002 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.

Building agents Claude Code Memory and context agent-skills ai-agents ai-assistant automation claudeclaw

migrate-memory

Migrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run after an update reports the shared-memory breaking change, or when a group still has .seed.md, legacy CLAUDE.md/CLAUDE.local.md, Claude auto-memory, or an unindexed imported-agent-memory.md.…

nanocoai/nanoclaw · 92 tokens

add-karpathy-llm-wiki

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

nanocoai/nanoclaw · 56 tokens

data-sync

Sync and archive data from messaging platforms (WhatsApp, Discord, Slack, Twitter/X, Google) into Moltis memory as daily digest summaries. Orchestrates crawl tools and writes structured markdown to the memory system.

moltis-org/moltis · 46 tokens

memory-management

Guide the agent to recall, remember, and route durable learning into Memory, Skills, Scheduled Tasks, or Tape.

ThinkInAIXYZ/deepchat · 26 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

nowledge-mem

Use Nowledge Mem for cross-tool startup context, recall of prior decisions, durable learnings, explicit conversation saving, and connection diagnosis. Use only the connection selected for this DeepChat agent or session.

ThinkInAIXYZ/deepchat · 45 tokens