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.
npx agentmods add skills/skynetcmd/m3-memory/m3-savenpx skills add skynetcmd/m3-memory --skill m3-savegit clone --depth 1 https://github.com/skynetcmd/m3-memoryWrote 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/skynetcmd/m3-memory/m3-save)<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>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 | $0.00019 | $0.00394 |
| Opus 5 | $0.00010 | $0.00197 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
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.
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:
- Look at the content the user gave you (
$ARGUMENTS) plus the last few turns of context. - Pick the most appropriate
typefrom this list:decision— choices made with a whyfact— verifiable assertion about the worldpreference— user's stated like / dislike / conventionnote— informal observation, doesn't fit other typestask— actionable item with statereference— pointer to external doc / URL / locationknowledge— durable understanding of how something worksobservation— what you noticed during a sessionsummary— distilled takeaway from a longer thread
- Pick
scope(default:user) — most personal facts/preferences are user-scoped; project knowledge often isn't. - Suggest a 1-line
titleif missing. - Show the user the proposed
{type, scope, title, content}and ask for a singleyto write, or any other key to abort. - On
y: callm3:memory_writewith those fields. - 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.
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.
- 5d ago First seen · 33 lines · 19 tokens per session scan A 975b3444b88b
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.
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…
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…
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…
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
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.
google-ads
Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.