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 wheregit 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/where)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/where"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/where/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/where"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/where.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 | $0.00147 | $0.04951 |
| Opus 5 | $0.00073 | $0.02475 |
| Sonnet 5 | $0.00029 | $0.00990 |
| Haiku 4.5 | $0.00015 | $0.00495 |
Grade A, and why
where 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
where
Purpose
Answer "where are we right now" in the time it takes to read a short message.
/where reads the present tense, including work still in flight. It answers from what is already
in the context window, plus one scoped read of this session's task entities — no transcript
reconstruction, no verification pass, no writes. That is the entire point: the operator asks this
question several times an hour, and a reconstruction that reads twenty thousand transcript lines
cannot be the answer to a question asked that often. One entity query can.
Brevity is the feature, not a side effect. A /where that runs as long as a /status has
failed even if every line in it is true.
The trio, by cost — not by lifecycle position
All three of these are distinct, and picking the wrong one is the failure this section exists to prevent. They are ordered by cost and confidence, not by where they sit in a session's life:
| Skill | Coverage | Verification | Writes | When |
|---|---|---|---|---|
/where |
in-context, plus one scoped task read |
none — everything unverified; stored task state is read, not checked | none | orientation, any time, often |
/status |
whole lineage, reconstructed from transcripts | every factual claim checked against its system of record | one session_digest |
when the read-out must be trustworthy |
/end |
whole session | audits storage and modeling | files tasks, persists entities, refreshes hubs | the actual close-out |
/status does NOT close a session. It is read-only for domain data and is designed to run
at any point mid-session; its single permitted write is bookkeeping about itself. /end is the
closing skill — it files, persists, and audits. Do not describe /status as a close-out, in this
skill or in a report; a session that believes it is will reach for the wrong tool at the wrong
moment.
Both /where and /status orient the operator, at very different cost. Neither closes anything.
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 · 316 lines · 147 tokens per session scan A e6d0dbdfb241
where is a skill published in the GitHub repository markmhendrickson/neotoma (32 stars, last pushed today), licensed MIT. It adds 147 tokens to every session and 4,951 once invoked, about $0.0007 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 2026-09-07.
Other skills, from other repositories
bernstein-plan
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.
bernstein-agents
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
bernstein-create-task
Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug fix, or queue up work for the orchestrator to handle.
ara-research-manager
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…
vp
Cross-cell coordination - resolve conflicts, decide pivots.