m3-write

m3-write is a skill for Claude Code, Codex from skynetcmd/m3-memory. It costs 26 tokens per session (154 once invoked), scanned A, original, Apache-2.0.

A direct note-writing routine for m3-memory, a local store for an agent’s long-term information. It saves the supplied text as a user note without automatically deciding what kind of information it is.

In plain words
What is it for?
Use it to write a note and receive its identifier, along with any notice that it replaces contradictory older information.
Why use it?
It gives you a predictable way to save a simple note when you do not want automatic classification.

Skill for Claude CodeCodex

Part of the m3 plugin — 16 skills, 15 commands, 2 agents, 3 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/skynetcmd/m3-memory/m3-write
Any agent
npx skills add skynetcmd/m3-memory --skill m3-write
Clone the repo
git clone --depth 1 https://github.com/skynetcmd/m3-memory

Made for: Claude Code, Codex.

Or install m3, the plugin that ships this one along with the rest of its 16 skills, 15 commands, 2 agents, 3 hooks, 1 MCP server.

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 m3-write

README.md
[![agentmods](https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-write.svg)](https://agentmods.dev/skills/skynetcmd/m3-memory/m3-write)
Your own site
<a href="https://agentmods.dev/skills/skynetcmd/m3-memory/m3-write"><img src="https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-write.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00154
Opus 5 $0.00013 $0.00077
Sonnet 5 $0.00005 $0.00031
Haiku 4.5 $0.00003 $0.00015

Measured 4d ago against content hash b084c21edc84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

m3-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 4d 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.

.antigravity-plugin/skills/m3-write/SKILL.md · 16 lines

What it actually says

M3 Write

When to Use

Use this skill when the user wants to explicitly write a simple note to their long-term memory without going through auto-classification.

Instructions

Call m3:memory_write with content="$ARGUMENTS", type="note", scope="user".

Report the resulting id and any contradiction events (memory_write returns supersede info if the new memory invalidates an older one).

If the user wanted a different type (decision, fact, preference, etc.), suggest /m3:save for the auto-classified path.

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. 4d ago First seen · 16 lines · 26 tokens per session scan A b084c21edc84

Subscribe to this mod's changes

m3-write is a skill published in the GitHub repository skynetcmd/m3-memory (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 26 tokens to every session and 154 once invoked, about $0.0001 per session on Opus 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.