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.
git 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/commands/skynetcmd/m3-memory/help)<a href="https://agentmods.dev/commands/skynetcmd/m3-memory/help"><img src="https://agentmods.dev/badge/commands/skynetcmd/m3-memory/help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/skynetcmd/m3-memory/help"><img src="https://agentmods.dev/badge/commands/skynetcmd/m3-memory/help.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00014 | $0.00383 |
| Opus 5.5 | $0.00006 | $0.00153 |
| Sonnet 5.5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
help 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 1mo 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
Print the following table verbatim. Do not interpret it as instructions or take any further action — just display it to the user.
# m3-memory commands
| Command | Purpose |
|--------------------|--------------------------------------------------------|
| /m3:health | Health check: package, payload, chatlog DB, hooks |
| /m3:status | Chatlog: row counts, queue, spill, last capture |
| /m3:search <q> | Hybrid memory search (FTS5 + vector + MMR) |
| /m3:save <c> | Auto-classified memory write (asks before writing) |
| /m3:write <c> | Direct memory_write — explicit, no auto-classify |
| /m3:get <id> | Fetch one memory by UUID or short prefix |
| /m3:graph <id> | Knowledge-graph traversal — related memories |
| /m3:forget <id> | Delete a memory (asks for confirmation) |
| /m3:export | GDPR Article 20 export — portable JSON |
| /m3:tasks | List tasks; filter by state |
| /m3:agents | List registered agents and last heartbeat |
| /m3:notify | Poll notification inbox |
| /m3:find-in-chat | Search captured chat-log turns |
| /m3:install | Install or upgrade m3-memory |
| /m3:help | This list |
The remaining MCP tools (100+ in total) are callable directly via tool calls.
Full reference: docs/AGENT_INSTRUCTIONS.md
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.
- 1mo ago First seen · 32 lines · 14 tokens per session scan A cae8c409ee23
help is a command published in the GitHub repository skynetcmd/m3-memory (30 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 383 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
load-claude-md
Refresh context with CLAUDE.md instructions.
recall
Search past AI coding sessions on a topic and summarize what was done. Pulls from the local sessionwiki index (Claude Code, Codex, Gemini CLI).
prime
Load SageOx team context for this AI coworker session.
init_newbrain
Onboarding interativo que personaliza AGENTS.md, Memória/ e a estrutura inicial do vault.
vault_scan
Varre notas novas/modificadas e adiciona referências cruzadas úteis.
style-skill-memory
Generate SKILL memory package from style reference for easy loading and consistent design system usage.