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 commands/skynetcmd/m3-memory/healthgit 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/health)<a href="https://agentmods.dev/commands/skynetcmd/m3-memory/health"><img src="https://agentmods.dev/badge/commands/skynetcmd/m3-memory/health.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 5.1 | $0.00022 | $0.00448 |
| Opus 5 | $0.00011 | $0.00224 |
| Sonnet 5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
health 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
Step 1 — run the doctor command, trying the resolvers below in order. Stop at the first one that returns exit 0; do not run the remaining ones.
# 1. Plain CLI, if mcp-memory is on PATH:
mcp-memory doctor
# 2. Module form, works whenever the m3_memory package is importable
# (catches pip install --user on Windows where the Scripts dir
# isn't on PATH, and any `pip install -e` dev checkout):
python -m m3_memory.cli doctor
# 3. Repo-local venv (developer case, run from the repo root):
.venv/Scripts/python.exe -m m3_memory.cli doctor # Windows
.venv/bin/python -m m3_memory.cli doctor # macOS/Linux
Step 2 — print the full doctor output verbatim (no paraphrasing).
Step 3 — append exactly ONE short line of interpretation. Examples:
all healthy.chatlog DB never captured — run /m3:install.Gemini SessionEnd hook off — run mcp-memory chatlog init --apply-gemini.
Do not write a paragraph. One line. The user can read the doctor output themselves.
Step 4 — if (and only if) doctor reported a repairable problem (a stale/dead agent
config path, a duplicate bridge, a disabled plugin, or a "run doctor --fix" hint),
OFFER to auto-repair. doctor --fix repoints dead config paths, de-duplicates MCP
registrations, and re-syncs agent hooks — it is non-destructive to data. Run the
same resolver that worked above, with --fix:
mcp-memory doctor --fix
# or: python -m m3_memory.cli doctor --fix
Then re-run plain doctor to confirm the fix took. If doctor was already all
healthy, do NOT run --fix.
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 · 44 lines · 22 tokens per session scan A 91f88976c389
health is a command published in the GitHub repository skynetcmd/m3-memory (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 448 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 commands, from other repositories
om-vault-upgrade
Import and migrate content from an existing Obsidian vault into this obsidian-mind instance. Works with older obsidian-mind versions and arbitrary Obsidian vaults.
om-correct
Sweep a corrected fact through the vault — finds every note restating it, applies the correction at the single source, replaces restatements with links, and preserves notes that correctly record what was believed at the time.
om-intake
Process all unread meeting notes in work/meetings/ — reads each file, classifies content, routes to the right vault notes, then clears the inbox.
om-dump
Freeform capture mode. Dump anything — conversations, decisions, incidents, wins, thoughts — and I'll route it all to the right notes with proper templates, frontmatter, and wikilinks.
load-claude-md
Refresh context with CLAUDE.md instructions.
ox-conversation
pinning, errors) belongs in the ox CLI JSON output (guidance field) and ox guide conversations, not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Read recorded team conversations locally: list, summaries, distillation topics, and transcript slices.