ateles: Skill for Claude Code

.claude/skills/store-neotoma/SKILL.md

store-neotoma is a skill for Claude Code from markmhendrickson/ateles. It costs 69 tokens per session (2,493 once invoked), scanned A, original, MIT.

A workflow for storing a chat in Neotoma, including the conversation, user and assistant messages, derived transcripts or analyses, and attachments. Neotoma is the system's single data store for this information.

In plain words
What is it for?
Use it when you need to archive the current chat, extract recoverable content, connect messages to the conversation, and report which records were affected.
Why use it?
It preserves useful conversation content and its relationships in a consistent structure, without requiring a separate intermediate storage format.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is markmhendrickson/ateles's own configuration. It tells Claude Code how to work on ateles itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ateles configures →

Reuse

Borrowing it

Nothing to install: this file belongs to markmhendrickson/ateles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/markmhendrickson/ateles/main/.claude/skills/store-neotoma/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

Wrote 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.

agentmods badge for store-neotoma

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/store-neotoma/github.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/store-neotoma)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/store-neotoma"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/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.

agentmods 80×15 button for store-neotoma

Your own site · 80×15
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/store-neotoma"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/store-neotoma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.02493
Opus 5 $0.00034 $0.01247
Sonnet 5 $0.00014 $0.00499
Haiku 4.5 $0.00007 $0.00249

Measured 5d ago against content hash d2be17c83cb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 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.

.claude/skills/store-neotoma/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 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 and storing it in Neotoma — conversation, dual agent_message rows per turn, derived transcript + analysis, and attachments — then reporting a succinct affected-records list. Neotoma is the only data store; there is no Parquet migration phase.

Execution policy (no confirmation gate)

/store_neotoma stores directly, then reports — it does NOT preview-and-wait. (Updated 2026-06-05 per operator: the prior mandatory preview/confirm gate is removed, matching /end.) Build the plan, execute the store, then render the affected-records summary. The user may still steer: if the user volunteers scope or "how to store" input (in their invocation or a follow-up), apply it; if they explicitly ask to see a preview first, honor that one-off request. Absent such input, do not block on confirmation.

Scope

Applies when the user asks to store the current chat in Neotoma. Covers extraction, storage, relationships, and reporting. 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 derived transcript and analysis synthesized from whatever the conversation actually provides (see below), plus attachments.

Prerequisites

  • Chat transcript available in agent context (user and agent messages).
  • Neotoma MCP available.
  • Load .cursor/rules/conversation_tracking.mdc and .cursor/rules/neotoma_harness.mdc for entity schemas and access rules. conversation_tracking defines dual-message + PART_OF; do not use merged role_user/role_agent on a single agent_message.

Phase 0: Extraction (build the store plan)

Step 0.1 — Extract

Parse all user and agent messages in the conversation. For each logical turn (user message + following assistant reply):

  • User row: entity_type: agent_message, role: "user", content = exact user text, turn_key (stable per turn), optional turn_number (1-based), timestamp, files_modified, tools_used, platform, model, neotoma_operations (inferred from the turn).
  • Assistant row: entity_type: agent_message, role: "assistant", content = exact assistant text shown in chat, turn_key e.g. same base + :assistant, optional same turn_number / timestamp for 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, correct, create_relationship).

Read the full file on GitHub · 125 lines

Changes

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.

  1. 5d ago First seen · 125 lines · 69 tokens per session scan A d2be17c83cb4

Subscribe to this mod's changes

store-neotoma is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 2,493 once invoked, about $0.0003 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 2026-09-03.