m3-save

m3-save is a skill for Claude Code, Codex from skynetcmd/m3-memory. It costs 19 tokens per session (394 once invoked), scanned A, original, Apache-2.0.

A memory-saving workflow that classifies information as a fact, decision, preference, task, note, or another type before writing it to m3 Memory. It asks for confirmation before saving.

In plain words
What is it for?
Use it to save durable project or personal information, suggest a title and scope, and confirm the content before it is added to memory.
Why use it?
It helps keep saved information organized and prevents an observation from being stored without the user reviewing what will be written.

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-save
Any agent
npx skills add skynetcmd/m3-memory --skill m3-save
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-save

README.md
[![agentmods](https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-save.svg)](https://agentmods.dev/skills/skynetcmd/m3-memory/m3-save)
Your own site
<a href="https://agentmods.dev/skills/skynetcmd/m3-memory/m3-save"><img src="https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-save.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 394 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 $0.00019 $0.00394
Opus 5 $0.00010 $0.00197
Sonnet 5 $0.00004 $0.00079
Haiku 4.5 $0.00002 $0.00039

Measured 5d ago against content hash 975b3444b88b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

m3-save 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 5d 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-save/SKILL.md · 33 lines

What it actually says

M3 Save

When to Use

Use this skill when you want to write a new observation, fact, decision, or preference to memory, and want the system to automatically classify its type, scope, and title while verifying it with the user first.

Instructions

Suggested save

You're about to write to m3-memory. Do not call memory_write yet. First propose a plan:

  1. Look at the content the user gave you ($ARGUMENTS) plus the last few turns of context.
  2. Pick the most appropriate type from this list:
    • decision — choices made with a why
    • fact — verifiable assertion about the world
    • preference — user's stated like / dislike / convention
    • note — informal observation, doesn't fit other types
    • task — actionable item with state
    • reference — pointer to external doc / URL / location
    • knowledge — durable understanding of how something works
    • observation — what you noticed during a session
    • summary — distilled takeaway from a longer thread
  3. Pick scope (default: user) — most personal facts/preferences are user-scoped; project knowledge often isn't.
  4. Suggest a 1-line title if missing.
  5. Show the user the proposed {type, scope, title, content} and ask for a single y to write, or any other key to abort.
  6. On y: call m3:memory_write with those fields.
  7. On abort: say "skipped" and stop.

Reasoning for the choices is fine to include but keep it short — the user wants speed, not a treatise.

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. 5d ago First seen · 33 lines · 19 tokens per session scan A 975b3444b88b

Subscribe to this mod's changes

m3-save is a skill published in the GitHub repository skynetcmd/m3-memory (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 394 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.

Related

Other skills, from other repositories

hermes3000-writing

Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API. Use for novels, fiction series, nonfiction books, whitepapers, long reads, chapter outlines, character/world-building, style guides, consistency memory, and DOCX/PDF/EPUB/HTML…

HybridAIOne/hybridclaw · 78 tokens

zettelkasten

Maintain a Luhmann-style Zettelkasten. Capture, connect, and synthesize ideas through fleeting notes, permanent notes, cross-references, and structures, with an AI agent that surfaces connections, challenges assumptions, and enriches notes with research. Use when the user shares an idea, observation, or inspiration…

HybridAIOne/hybridclaw · 89 tokens

qmd

Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…

breferrari/obsidian-mind · 142 tokens

knowledge_base

Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.

siddsachar/row-bot · 19 tokens

hue

Read and control Philips Hue Bridge lighting installations through local CLIP v2 or the Hue Remote API with SecretRef-backed credentials and guarded lighting changes.

HybridAIOne/hybridclaw · 32 tokens

google-ads

Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.

HybridAIOne/hybridclaw · 29 tokens