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-guidenpx skills add skynetcmd/m3-memory --skill m3-guidegit 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-guide)<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>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 | $0.00051 | $0.00691 |
| Opus 5 | $0.00026 | $0.00345 |
| Sonnet 5 | $0.00010 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
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.
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_searchbefore 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_writeit — decisions, corrections, runbooks, preferences. - Update, don't duplicate. Search before writing; prefer
memory_updateormemory_supersede(retires the old claim with asupersedesedge, keeps history) over a near-duplicate. Duplicates degrade later retrieval. - Link. Reference related memories as
[[name]]somemory_graphtraversal 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.
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 · 65 lines · 51 tokens per session scan A 59ea14b15dd6
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.
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.