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/ateles --skill neotoma-learngit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/ateles/neotoma-learn)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/neotoma-learn"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/neotoma-learn.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high System Prompt Leakage · line 103 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Excessive Agency · line 77 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.
- low Excessive Agency · line 41 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00029 | $0.04781 |
| Opus 5 | $0.00015 | $0.02390 |
| Sonnet 5 | $0.00006 | $0.00956 |
| Haiku 4.5 | $0.00003 | $0.00478 |
Grade A, and why
neotoma-learn 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 7d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
neotoma-learn
Purpose
Define how to update the Neotoma MCP instructions file so agents both store and retrieve data correctly with Neotoma per observed failures or scenarios. Storage gaps (missed same-turn persistence, missing provenance, missed attachments) and retrieval gaps (skipped bounded retrieval, wrong query shape, ignored retrieved context, count/recency mis-queries) are equally in scope.
The skill also audits compliance with other Neotoma-related workspace rules in this repo (for example the consolidated always-on harness in neotoma_harness.mdc, the skills-source-of-truth and stub-fetch contract in skills_neotoma_proactive_fetch, the post-edit cache regeneration contract in post_updates_neotoma_cache, etc.). When a rule was not followed, apply the fix in the correct location per the durable-enhancement ladder — usually by strengthening the Neotoma MCP instructions, but sometimes by strengthening the workspace rule file itself.
Scope
Applies when the user invokes /neotoma_learn in this repository. Target file is the sibling Neotoma repo instructions document.
When invoked (optionally with a scenario, report path, or failure description), follow the workflow below. When no scenario is provided, the default behavior is to interrogate the most recent conversational turn to determine whether the Neotoma MCP was used as expected, and apply a fix only if a gap is identified.
When to use
Use when the user wants Neotoma MCP instructions strengthened so agents store and retrieve data correctly — for example same-turn storage when pulling data from other MCPs, a missed bounded retrieval at turn start, an answer that ignored relevant retrieved context, or a specific failure observed in chat.
Target files
Primary target (Neotoma MCP instructions, most gaps land here):
- Path:
../neotoma/docs/developer/mcp/instructions.md(relative to ateles repo root). Resolve absolute path if needed. - Constraint: edit only within the first fenced code block in that file. Do not change markdown structure (headers, related docs, closing fence). Do not edit
neotoma/src/server.tsfallback array.
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.
- 7d ago First seen · 178 lines · 29 tokens per session scan A d311b06d3db1
neotoma-learn is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 4,781 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
local-llm-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
aaai
AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.
colm
COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.
conference-research
Academic venue paper discovery — activate when you need to find papers accepted at specific conferences or journals (ACL, EMNLP, NeurIPS, ICML, ICLR, MLSys, etc.), analyze venue acceptance preferences, or look up CFP requirements.
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.