m3-guide

m3-guide is a skill for Claude Code, Codex from skynetcmd/m3-memory. It costs 51 tokens per session (691 once invoked), scanned A, original, Apache-2.0.

A usage guide for m3, a memory system that stores information between coding sessions. It explains which memory tools to use and how to check that conversation capture is working.

In plain words
What is it for?
It helps search stored memories, record important findings, update outdated information, and verify that chat history is being saved.
Why use it?
It helps prevent lost decisions, repeated investigation, and reliance on outdated session context.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-guide.svg)](https://agentmods.dev/skills/skynetcmd/m3-memory/m3-guide)
Your own site
<a href="https://agentmods.dev/skills/skynetcmd/m3-memory/m3-guide"><img src="https://agentmods.dev/badge/skills/skynetcmd/m3-memory/m3-guide.svg" alt="Measured on agentmods" 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 691 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 $0.00051 $0.00691
Opus 5 $0.00026 $0.00345
Sonnet 5 $0.00010 $0.00138
Haiku 4.5 $0.00005 $0.00069

Measured 5d ago against content hash 59ea14b15dd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

m3-guide 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-guide/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using m3 Memory

Tool names and signatures come from the MCP tool list. This is the part that isn't in a tool description: the protocol, and the traps.

Trust order

m3 memory > artifacts (git, handoff files) > session context. When m3 contradicts what you think you remember, trust m3 — context degrades across session boundaries, memory does not.

Verify capture is live

Registered ≠ working. The server can be connected while chatlog capture is silently dead. Call chatlog_status once early in a substantive session. If hooks are off or last_write is null/stale, say so loudly and don't proceed silently — a dead chatlog means this session's decisions vanish at the next session boundary. Never degrade quietly to flat files.

Protocol

  • Search first. memory_search before re-deriving anything about this user, project, or machine. A settled decision re-litigated is a bug reintroduced.
  • Write as you go. If it took effort to learn and will matter later, memory_write it — decisions, corrections, runbooks, preferences.
  • Update, don't duplicate. Search before writing; prefer memory_update or memory_supersede (retires the old claim with a supersedes edge, keeps history) over a near-duplicate. Duplicates degrade later retrieval.
  • Link. Reference related memories as [[name]] so memory_graph traversal stays useful.

Chat log

Captured turns from host agents live in a store separate from curated memory. Reach them with chatlog_search, chatlog_list_conversations, and chatlog_promote (promotes turns into curated memory).

⚠️ Never open a database file directly

The chat store and main store may be two databases, one unified database, or PostgreSQL — a deployment choice only the tools know.

Querying agent_memory.db for type='chat_log' returns zero rows on a split deployment even when capture is perfectly healthy — a false emergency. On a PostgreSQL primary there's no local file at all. Use chatlog_status; m3 chatlog status --json reports unified: true|false if you need the topology.

Read the full file on GitHub · 65 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. 5d ago First seen · 65 lines · 51 tokens per session scan A 59ea14b15dd6

Subscribe to this mod's changes

m3-guide is a skill published in the GitHub repository skynetcmd/m3-memory (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 691 once invoked, about $0.0003 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