agentmods.dev

mt-write

mt-write is a skill for Claude Code, Codex from hanyki111/memory_tool. It costs 66 tokens per session (499 once invoked), scanned A, original, MIT.

A guided writing helper for knowledge documents. It asks questions, checks what the user writes, helps choose a document type, and creates the document only when the user is ready.

In plain words
What is it for?
Use it to plan, review, outline, and create a knowledge-base document from the user's own ideas.
Why use it?
It prevents writing an unnecessary document or drafting content the user has not supplied. It also helps find an existing document before creating a duplicate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 11repo yesterday A scan 66 tokens original MIT

Good fit Use it to plan, review, outline, and create a knowledge-base document from the user's own ideas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hanyki111/memory_tool/mt-write
View source ↗ hanyki111/memory_tool
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 hanyki111/memory_tool --skill mt-write
Clone the repo
git clone --depth 1 https://github.com/hanyki111/memory_tool

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.

agentmods badge for mt-write

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hanyki111/memory_tool/mt-write"><img src="https://agentmods.dev/badge/skills/hanyki111/memory_tool/mt-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00499
Opus 5.5 $0.00026 $0.00200
Sonnet 5.5 $0.00013 $0.00100
Haiku 4.5 $0.00007 $0.00050

Measured today against content hash c999e3b95c85, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mt-write 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.

memory_tool/templates/skills/mt-write/SKILL.md · 52 lines

What it actually says

MT-Write: Writing Support

The user writes. You ask, check and point things out.

The user keeps a knowledge base partly to keep their own reading and writing skills. Do not draft a document unless they ask for one.

Procedure

  1. Load the guides. They hold the questions and checks, and the user may have customised them.

    mmodule guide            # shared rules and how to choose a type
mmodule guide <type>     # 참고, 이해, 방법 or 판단

  2. Check that a new document is needed. Search first with ms "<topic>". Prefer updating an existing document. Things not worth finding again belong in the timeline (m "...").

  3. Settle the type and the one-sentence description with the user. If the choice is unclear, leave the type empty. It is optional.

  4. Create the document only when the user is ready to write.

    mmodule create "<path>" --type <type> --desc "<one sentence>"

    This writes frontmatter and a title. Do not add headings or placeholders to it.

  5. Follow the guide's order: ask, point out problems after they write, offer an outline when they are stuck, and write for them only on request.

When you write the body yourself

Only after an explicit request. Record it in the frontmatter so that the user can tell how much they wrote themselves:

generated:
  by: <producer>/<version>

Use --by when creating the document, or edit the field when taking over an existing one. Text the user wrote stays human:<id>.

Do not

  • Copy a guide's questions into the document as headings.
  • Add empty sections or TODO markers.
  • Rewrite the user's sentences unasked. Point at the problem and let them fix it.
  • Change a judgment document's conclusion after the fact. A new judgment gets its own document, linked to the old one.
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 First seen · 52 lines · 66 tokens per session scan A c999e3b95c85

Subscribe to this mod's changes

mt-write is a skill published in the GitHub repository hanyki111/memory_tool (11 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 499 once invoked, about $0.0003 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 2026-11-06.

PlanningWriting and docs
Related

mt-write compared with skills from other repositories

mt-write next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mt-writehanyki111/memory_toolSkill11yesterdayMITA66Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code