Borrowing it
Nothing to install: this file belongs to hanyki111/memory_tool. 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/hanyki111/memory_tool/main/.claude/skills/mt-master-module/SKILL.mdgit clone --depth 1 https://github.com/hanyki111/memory_toolWrote 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/hanyki111/memory_tool/mt-master-module)<a href="https://agentmods.dev/skills/hanyki111/memory_tool/mt-master-module"><img src="https://agentmods.dev/badge/skills/hanyki111/memory_tool/mt-master-module/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/hanyki111/memory_tool/mt-master-module"><img src="https://agentmods.dev/badge/skills/hanyki111/memory_tool/mt-master-module.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 | $0.00042 | $0.01303 |
| Opus 5.5 | $0.00017 | $0.00521 |
| Sonnet 5.5 | $0.00008 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade B, and why
mt-master-module scanned grade B with 1 finding 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/memory-context.md How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MT-Master-Module: Project Overview Creator
"One document to represent your entire project."
This skill creates a comprehensive project overview document that serves as the entry point for understanding a project in the federated knowledge system.
When to Use
- User explicitly requests: "마스터 모듈 만들어줘", "create master module", "프로젝트 개요 만들어줘"
- Project is mature enough to summarize
- Preparing for KB federation (multiple projects sharing knowledge)
For publishing specific modules, use mt-publish instead.
Workflow
Phase 1: Gather Information
Read project context:
cat .claude/memory-context.md
cat CLAUDE.md
mmodule tree
Review key modules:
mmodule tree
# Read the documents the tree lists. Decisions are also in the timeline: ms "Decision:"
Check timeline for milestones:
mweek
mtoday
Phase 2: Create Master Module
Create module structure:
mmodule create master
This creates .memory/modules/master.md locally.
When published, the registry key automatically includes project name prefix
(e.g., memory-tool/master) to avoid collisions across projects.
The document holds the project overview and a summary of architectural decisions.
Phase 3: Write Content
Master module outline:
# [Project Name] - Master Module
> One-sentence project description
## Project Identity
- **Name:** [Project Name]
- **Purpose:** [Core problem being solved]
- **Started:** [Date]
- **Status:** [Active/Maintenance/Archived]
## Tech Stack
| Layer | Technology | Rationale |
|-------|------------|-----------|
| Language | Python 3.10+ | Type hints, async support |
| Database | SQLite | Zero-config, portable |
| CLI | Click | Decorator-based, composable |
## Architecture Overview
[High-level architecture diagram or description]
### Key Components
1. **Component A** - [Purpose]
2. **Component B** - [Purpose]
3. **Component C** - [Purpose]
## Module Index
| Module | Purpose | Status |
|--------|---------|--------|
| core-system | Timeline and initialization | Active |
| search-system | Text and semantic search | Active |
| ui-system | CLI and TUI interfaces | Active |
## Key Decisions
| Decision | Rationale | Date |
|----------|-----------|------|
| SQLite for storage | Zero-config, portable | 2025-01 |
| BM25 for search | Fast, no dependencies | 2025-02 |
## Lessons Learned
### What Worked Well
- [Pattern or approach that succeeded]
- [Another success]
### What We'd Do Differently
- [Retrospective insight]
- [Another insight]
## Getting Started
```bash
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.
- today Changed · -6 lines 1115b401b325
- 2mo ago First seen · 245 lines · 42 tokens per session scan B 7fe96999e903
mt-master-module is a skill published in the GitHub repository hanyki111/memory_tool (11 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,303 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
mt-master-module compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mt-master-modulehanyki111/memory_tool | Skill | 11 | yesterday | MIT | B | 42 | Claude Code |
| cua-volumetrycua/cua | Skill | 32k | today | MIT | A | 114 | Claude Code, Codex |
| obsidiansteipete/agent-scripts | Skill | 7.5k | 7d ago | MIT | A | 19 | Claude Code, Codex |
| loopx-doc-registryhuangruiteng/loopx | Skill | 6.5k | 5d ago | Apache-2.0 | A | 74 | Codex |
| docxMemTensor/memmy-agent | Skill | 2.2k | today | MIT | A | 40 | Claude Code, Codex |
| pptxMemTensor/memmy-agent | Skill | 2.2k | today | MIT | A | 29 | Claude Code, Codex |
| xlsxMemTensor/memmy-agent | Skill | 2.2k | today | MIT | A | 35 | Claude Code, Codex |