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 store_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/store_neotoma)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/store_neotoma"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/store_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/store_neotoma"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/store_neotoma.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 | $0.00009 | $0.02302 |
| Opus 5 | $0.00005 | $0.01151 |
| Sonnet 5 | $0.00002 | $0.00460 |
| Haiku 4.5 | $0.00001 | $0.00230 |
Grade A, and why
store_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 11d 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.
This is a copy
88% identical to store-neotoma — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
store-neotoma
Purpose
Define the workflow for reviewing chat, building a Neotoma store preview, and executing storage after user confirmation. Neotoma is the only data store; there is no Parquet migration phase.
Canonical location: foundation/.cursor/skills/store-neotoma/SKILL.md (foundation git submodule). Consumer repos may symlink or copy this into .cursor/skills/store-neotoma/ via setup_cursor_copies / setup_cursor_rules.
Scope
Applies when the user asks to store the current chat in Neotoma. Covers preview, user revisions, confirmation, storage, and relationships. Excludes one-off store operations without preview.
Reviews the current chat conversation, builds a preview of records to store in Neotoma, waits for user confirmation (or revision input), then stores conversation, two agent_message entities per logical turn (role: "user" and role: "assistant"), each with PART_OF → conversation — the canonical shape from Neotoma MCP live chat instructions — plus attachments.
Preview-before-execute: On first run, this workflow MUST preview what will be stored and MUST NOT execute storage until the user confirms. User input (corrections, scope changes, exclusions) MUST be applied to revise the preview.
Prerequisites
- Chat transcript available in agent context (user and agent messages).
- Neotoma MCP available.
- Load
.claude/rules/conversation_tracking.mdcand.claude/rules/neotoma_access_policy.mdcfor entity schemas and access rules.conversation_trackingdefines dual-message +PART_OF; do not use mergedrole_user/role_agenton a singleagent_message.
Phase 0: Preview (MANDATORY — Execute First)
Step 0.1 — Extract and build preview
Parse all user and agent messages in the conversation. For each logical turn (user message + following assistant reply):
- User row (preview + store):
entity_type: agent_message,role: "user",content= exact user text,turn_key(stable per turn), optionalturn_number(1-based),timestamp,files_modified,tools_used,platform,model,neotoma_operations(inferred from the turn). - Assistant row (preview + store):
entity_type: agent_message,role: "assistant",content= exact assistant text shown in chat,turn_keye.g. same base +:assistant, optional sameturn_number/timestampfor sorting. - Topics: extract from user questions, entity types discussed, file paths, domain keywords (finance, admin, health, work).
- Decisions: extract when agent states an approach, user confirms a choice, or implementation strategy is chosen.
- Action items: tasks to create, follow-ups mentioned.
files_modified: file paths from tool calls, @-mentions, or explicit file references (typically attributed to the user message for that turn).neotoma_operations: inferred from agent tool-call patterns (store_structured,correct,create_relationship).
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.
- 11d ago First seen · 145 lines · 9 tokens per session scan A ab934643d074
store_neotoma is a skill published in the GitHub repository markmhendrickson/neotoma (32 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 2,302 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to store-neotoma, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
architecture-paradigm-cqrs-es
Applies CQRS and Event Sourcing for read/write separation and audit trails. Use when designing systems with complex domain logic or full state-change history.
backend-event-sourcing
Use this skill when the user says 'event sourcing', 'event store', 'event stream', 'event sourced', 'rehydrate from events', 'event replay', 'projection rebuild', 'event log', 'append-only log', 'event history'. This skill enforces: events as the single source of truth, current state derived from event replay…
cratis-readmodel
Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…
cratis-arc-ef-core-migration
Change an Entity Framework Core schema in a Cratis Arc application — the DbContext base types Arc provides, the cross-database column helpers, JSON columns, how a migration is created and applied, and how an EF Core read model becomes injectable into a command. Use when adding or changing a table, column…
cratis-chronicle-event-type-migration
Evolve a Chronicle event schema without breaking replay - add a generation and an EventTypeMigration so stored events upcast into the new shape. Use when an event needs a new required property, a renamed or split property, a structural change, or a changed enum value after events of the prior shape already exist. Do…
cratis-chronicle-event-constraints
Enforce append-time uniqueness in Chronicle with the [Unique] attribute, [RemoveConstraint], and IConstraint, and specify the violation with EventScenario. Use when a rule must hold at the event store rather than in a command, so two concurrent appends cannot both win. Do not use for ordinary command input validation…