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 skills add markmhendrickson/neotoma --skill ensure-neotomagit clone --depth 1 https://github.com/markmhendrickson/neotomaWrote 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/markmhendrickson/neotoma/ensure-neotoma)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/ensure-neotoma"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/ensure-neotoma/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/skills/markmhendrickson/neotoma/ensure-neotoma"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/ensure-neotoma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 29 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 81 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00028 | $0.00623 |
| Opus 5.5 | $0.00011 | $0.00249 |
| Sonnet 5.5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
ensure-neotoma 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 29d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensure Neotoma
Meta skill that installs and configures Neotoma so other memory skills can run. Every remember-* skill references this as a prerequisite.
When to use
- Before running any
remember-*skill for the first time. - When the user says "install neotoma", "set up memory", or similar.
- When another skill fails because Neotoma MCP is not connected.
Workflow
Phase 1: Check if Neotoma CLI is available
npx neotoma status --output json
If neotoma is not found or status reports installed: false:
- Guide installation:
npm install -g neotoma - Verify the install succeeded:
neotoma --version
Phase 2: Run setup
Run the composite setup command to configure MCP, CLI instructions, hooks, permissions, and skills for the current harness:
neotoma setup --yes
If the user wants to target a specific harness, pass --tool:
neotoma setup --tool cursor --yes
neotoma setup --tool claude-code --yes
neotoma setup --tool codex --yes
Review the setup report. Every step should show ok: true. If any step failed, report the failure reason and suggest remediation.
Phase 3: Verify MCP connectivity
Use the Neotoma MCP get_session_identity tool to confirm the MCP connection is live:
- If the tool is available and returns a response, Neotoma is configured.
- Check
attribution.tier—softwareorhardwaremeans verified attribution;unverified_clientis functional but unverified. - If the MCP tool is not available, check the harness MCP config file and guide the user through manual configuration.
Phase 4: Confirm readiness
Report the result:
- Neotoma version installed
- Harness detected and configured
- MCP connectivity status
- Attribution tier
State that the user can now run any remember-* skill, and that ordinary
storage and retrieval (store, query, recall) work directly through the live
MCP tool instructions without loading a separate skill.
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.
- 29d ago Changed · +2 lines 922e8f9567fa
- 1mo ago First seen · 84 lines · 28 tokens per session scan A 2a8b16f1db06
ensure-neotoma is a skill published in the GitHub repository markmhendrickson/neotoma (34 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 623 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 2026-09-03.
Other skills, from other repositories
taste-companion
A general conversation and recommendation skill that remembers confirmed preferences, searches past chats, and uses recommendations and viewing data to help a person decide what to watch or discuss.
taste-explorer
A guided interview skill that asks focused questions to learn what a person likes and dislikes, then saves confirmed preferences as long-term memory.
akf
AKF, the AI native file format (EXIF for AI) — check before you trust, stamp what you verify. A stamp costs 15 tokens; re-verifying costs 15,000.
akf
AKF, the AI native file format (EXIF for AI) — check before you trust, stamp what you verify. Use before building on existing files, after completing verified work, and when handling agent memories or downloaded skills.
core-memory
Use when working with Core Memory from OpenClaw, including finalized-turn writes, memory retrieval, bridge behavior, semantic bead fields, promotion, claims, associations, or integration debugging.
soul-archive
Soul Archive — digital personality persistence + agentic memory. Builds your digital soul clone through everyday AI conversations: persona injection at session start, cross-session recall, failure-pattern warning, pattern distillation. Conversation-end auto sedimentation (autoextract defaults ON). All data local…