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 skills/markmhendrickson/neotoma/start-sessionnpx skills add markmhendrickson/neotoma --skill start-sessiongit 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/start-session)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/start-session"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/start-session.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 | $0.00059 | $0.00860 |
| Opus 5 | $0.00030 | $0.00430 |
| Sonnet 5 | $0.00012 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
start-session 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
start-session
Specification status: This file is a specification, not a runnable skill. The core_workflows bundle is defined in m1 of the Bundles Strategy (plan ent_089da2ecebc3bd804d63dcf2); the runtime path that installs and auto-loads these skills lands in m2 alongside plan ent_b5a51d1395d206e10945b6b1 (Resolve #205). Until m2, treat this file as the locked spec the implementation MUST match.
Adapted in structure from the reference implementation in lemon-skills-share (https://github.com/Lemonbrand/lemon-skills-share). Neotoma's version uses the Neotoma MCP and CLI for state-layer access rather than the reference's bespoke knowledge-base API.
Purpose
Every work session follows the same shape: get context, do work, close session. This skill owns the first leg. By the time it finishes, the agent knows what's on the schedule, who matters today, what's still open from prior sessions, and what's new since last close.
The principle: do not start work by reacting to whatever surfaces first. Orient, then act.
When to use
- The first prompt of every working session.
- Returning after a long gap (more than four hours) when fresh state is needed.
- After any unattended period (overnight, weekend, travel).
- Whenever the user says "let's start", "ok let's go", "what's on the docket", or "where are we".
Skip when:
- The user has already given a concrete task and explicitly says "skip the intro".
- The agent is inside a sub-agent invocation (the parent owns context).
Required entity types
contact, event, task, observation. All are provided by the default-install core bundle.
Process
Step 1: Health check
Verify the Neotoma state layer is reachable. If it is not, every downstream step degrades to best-effort and the user MUST be told.
Step 2: Strategic snapshot
Pull the most-recently-touched entities to surface anything needing attention before the user asks. Source: Neotoma list_recent_changes over the last 24 hours.
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.
- yesterday First seen · 81 lines · 59 tokens per session scan A 1dfc321a02f9
start-session is a skill published in the GitHub repository markmhendrickson/neotoma (31 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 860 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.
Other skills, from other repositories
setup-brain
Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.
evolve
Use when many related hardened instincts (high-confidence feedback/discovery memories) have piled up in one domain, when the user runs /evolve or asks to promote, cluster, graduate, or consolidate accumulated instincts into a Command, Skill, or Agent, or when files in Instinct Proposals need review. Part of the…
remember
Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.
jumbo-add-guideline
Use liberally when the user expresses a preference about how work should be done — coding style, process, testing approach, communication style. Captures the guideline so future sessions follow it without being told again.
atomicmemory-cli
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.