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 skills add NeuroGhostDev/booster_mcp --skill booster-project-memorygit clone --depth 1 https://github.com/NeuroGhostDev/booster_mcpWrote 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/skills/neuroghostdev/booster_mcp/booster-project-memory)<a href="https://agentmods.dev/skills/neuroghostdev/booster_mcp/booster-project-memory"><img src="https://agentmods.dev/badge/skills/neuroghostdev/booster_mcp/booster-project-memory/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/skills/neuroghostdev/booster_mcp/booster-project-memory"><img src="https://agentmods.dev/badge/skills/neuroghostdev/booster_mcp/booster-project-memory.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 | $0.00038 | $0.00502 |
| Opus 5.5 | $0.00015 | $0.00201 |
| Sonnet 5.5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
booster-project-memory 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.
What it actually says
Booster Project Memory
Цель
project_memory позволяет сохранять важную информацию (контекст, архитектурные решения, TO-DO) в .agents/booster/memory.json. Это нужно, чтобы агент не "забывал" важные детали при перезапусках и смене сессий.
В Cognitive Runtime добавлены структурированные факты:
remember_project_fact(category, fact, confidence, source, repo)project_memory_recall(query, categories, repo, limit)
Они живут в том же memory.json, но имеют категории, confidence и источник.
Как использовать
-
Сохранение (set): При нахождении важного архитектурного инсайта или зависимости:
project_memory(action="set", key="architecture:auth", value="Авторизация использует JWT через кастомный middleware в src/auth.py") -
Чтение (get): При старте работы (особенно в новом чате):
project_memory(action="get", key="architecture:auth") -
Список ключей (list): Чтобы узнать, какие знания уже сохранены по проекту:
project_memory(action="list", key="") -
Структурированный recall перед задачей: Перед изменением кода:
project_memory_recall(query="добавить OAuth в auth flow") -
Сохранение проверенного факта: После анализа архитектуры:
remember_project_fact(category="architecture", fact="Frontend ходит в backend только через BFF", confidence=0.95, source="repo_map+impact_analysis") -
Удаление (delete) и очистка (clear): Если информация устарела:
project_memory(action="delete", key="architecture:auth")project_memory(action="clear", key="")# Очистить всю память
Антипаттерны
- Не сохраняй огромные куски кода в память (сохраняй выводы и ссылки на файлы).
- Если проект переписывается, обновляй старые записи в памяти.
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 · 52 lines · 38 tokens per session scan A cca098cf28d7
booster-project-memory is a skill published in the GitHub repository NeuroGhostDev/booster_mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 502 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 2026-08-31.
Other skills, from other repositories
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
maintain-context
A maintenance workflow for the files that explain a project to coding agents, such as AGENTS.md, skills, and documentation. It checks whether those files still match the code and processes a learning inbox of discovered corrections and facts.
contorium-workspace-memory
Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
zenpass-ai-skill
Portable personal AI context passport and sovereign identity protocol distilled from Egoist Machines (YC S26). Eliminates agent context silos by allowing consumers to own, inspect, and securely port their sizing, aesthetic tastes, allergies, and budget constraints across disparate shopping and decision agents with…