memory_tool: Skill for Claude Code

.claude/skills/mt-publish/SKILL.md

mt-publish is a skill for Claude Code from hanyki111/memory_tool. It costs 51 tokens per session (1,184 once invoked), scanned A, original, MIT.

A module-publishing workflow that turns project-specific technical knowledge into reusable material for a central knowledge base.

In plain words
What is it for?
Reviewing a module, generalizing its architecture and examples, documenting dependencies, and publishing the refined knowledge.
Why use it?
It removes project-specific details and makes useful patterns, solutions, and decisions easier to share across projects.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is hanyki111/memory_tool's own configuration. It tells Claude Code how to work on memory_tool 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 memory_tool configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/hanyki111/memory_tool/main/.claude/skills/mt-publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hanyki111/memory_tool

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 mt-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/hanyki111/memory_tool/mt-publish/github.svg)](https://agentmods.dev/skills/hanyki111/memory_tool/mt-publish)
Your own site
<a href="https://agentmods.dev/skills/hanyki111/memory_tool/mt-publish"><img src="https://agentmods.dev/badge/skills/hanyki111/memory_tool/mt-publish/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 mt-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/hanyki111/memory_tool/mt-publish"><img src="https://agentmods.dev/badge/skills/hanyki111/memory_tool/mt-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00051 $0.01184
Opus 5.5 $0.00020 $0.00474
Sonnet 5.5 $0.00010 $0.00237
Haiku 4.5 $0.00005 $0.00118

Measured today against content hash 7c982d074040, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mt-publish 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 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.

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/skills/mt-publish/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MT-Publish: Module Publisher

"Execution should be isolated, but Knowledge must be federated."

This skill helps refine a specific module's knowledge into reusable, context-independent artifacts and publish them to the central Knowledge Base.

When to Use

  • User explicitly requests: "KB에 발행해줘", "publish to KB", "모듈 발행해줘"
  • User wants to share a specific module's learnings
  • Module is mature and worth preserving

For project-wide overview, use mt-master-module instead.

Workflow

Phase 1: Analyze (분석)

Review target module:

ls .memory/modules/<path>*
# Read <path>.md or <path>/<name>.md. Older modules use current.md and decisions.md.

Identify publishable content:

  • Core patterns and architectures
  • Reusable solutions
  • Key decisions with rationale

Phase 2: Refine (정제)

De-contextualization:

  • Remove project-specific paths, variable names
  • Generalize code examples
  • Make dependencies explicit

Before (project-specific):

from myproject.auth import JWTHandler
db = connect("postgres://myproject:pass@localhost/mydb")

After (generalized):

# Requires: pyjwt, psycopg2
from auth_module import JWTHandler  # Your JWT implementation
db = connect(DATABASE_URL)  # Set via environment variable

Add explicit dependencies:

## Prerequisites
- Python 3.10+
- PostgreSQL 14+
- Required packages: pyjwt, psycopg2

Phase 3: Validate (검증)

Self-check question:

"이 문서만 보고, 빈 프로젝트에서 해당 기능을 구현할 수 있는가?"

If missing information, add:

  • Environment variables needed
  • Database schema
  • External service setup
  • Configuration files

Phase 4: Publish (발행)

Preview first:

mpublish <module-name> --dry-run

Publish with metadata:

mpublish <module-name> --tags auth,security,jwt

Verify:

mimport --list
KB Path Structure

mpublish creates files at:

{KB_PATH}/modules/{category}/{project_name}/{module_name}/
Parameter Default Description
category Projects Use --category Topics for topic-based modules
project_name Auto-detected From directory name or config.yaml
module_name Local module name e.g., search-system

Read the full file on GitHub · 203 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. today Changed · -1 lines 7c982d074040
  2. 2mo ago First seen · 204 lines · 51 tokens per session scan A b633ed03a235

Subscribe to this mod's changes

mt-publish is a skill published in the GitHub repository hanyki111/memory_tool (11 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,184 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.

Related

mt-publish compared with skills from other repositories

mt-publish next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mt-publishhanyki111/memory_toolSkill11yesterdayMITA51Claude Code
orbit-notionnexu-io/open-designSkill106kyesterdayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k2d agoApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
ppt-reviewOrkas-AI/OrkasSkill9.0ktodayMITA2Claude Code, Codex
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex