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/install)<a href="https://agentmods.dev/commands/skynetcmd/m3-memory/install"><img src="https://agentmods.dev/badge/commands/skynetcmd/m3-memory/install/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/install"><img src="https://agentmods.dev/badge/commands/skynetcmd/m3-memory/install.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 | $0.00326 |
| Opus 5.5 | $0.00006 | $0.00130 |
| Sonnet 5.5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade C, and why
install scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/skynetcmd/m3-memory/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/skynetcmd/m3-memory/main/install.sh | bash What it actually says
m3-memory install / upgrade
Step 1 — detect current state. Try in order:
mcp-memory --version # plain CLI
python -m m3_memory.cli --version # module form (Windows --user)
Step 2 — branch on what step 1 printed.
Not installed (both commands fail):
- On Linux / macOS, suggest:
curl -fsSL https://raw.githubusercontent.com/skynetcmd/m3-memory/main/install.sh | bash - On Windows, suggest:
Link them topip install --user m3-memory # then add %APPDATA%\Python\Python<NN>\Scripts to user PATH if neededhttps://github.com/skynetcmd/m3-memory/blob/main/docs/install_windows.mdfor full instructions.
After install completes, tell the user to re-run /m3:health in a NEW Claude Code session (PATH changes don't apply to the current one).
Already installed (a version printed):
- On Linux / macOS, run:
pipx upgrade m3-memory mcp-memory update - On Windows, run:
pip install --user --upgrade m3-memory python -m m3_memory.cli update - Then
/m3:healthto verify.
Step 3 — print one-line summary of what action was taken or recommended.
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 · 45 lines · 14 tokens per session scan C fbfc5c5da597
install is a command published in the GitHub repository skynetcmd/m3-memory (29 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 326 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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.
memory-bootstrap
One-time setup of a foundational Aionforge Memory substrate for a fresh project.