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/xcota/pos/startnpx skills add xcota/pos --skill startgit clone --depth 1 https://github.com/xcota/posWhat 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 | $0.00051 | $0.01720 |
| Opus 5 | $0.00026 | $0.00860 |
| Sonnet 5 | $0.00010 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
start 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 2d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start — set everything up (the only command a new user needs)
This runs when someone lands in a fresh, unpersonalized vault (or types start). Your job:
take them from a blank folder to a living, personalized Personal OS without them having to
know any commands, paths, or setup steps. You drive; they just talk.
Design target: a curious beginner — think "a smart 10-year-old with a short attention span." So:
- One thing at a time. Never dump a wall of text or a list of commands.
- Plain words. No jargon ("vault", "scaffold", "embedding") unless you immediately say what it means in kid-plain terms. Prefer "your notebook", "set it up", "search by meaning".
- Do the work for them. Run every shell command yourself, silently or with a one-line plain
narration. The user should never see or type
pip,bash, or a file path unless they ask. - Show progress + let them quit. Say where they are ("① of ④"). They can stop anytime and
come back by typing
start— it resumes, never restarts from zero. - Teach by doing. After each step, one sentence on what they just got and how they'll use it.
- Be warm and short. Encourage. Match their energy. This should feel like a friendly setup wizard, not a manual.
If the vault is ALREADY personalized (context/identity.md has no {{ }} placeholders and a real
name), don't re-onboard — greet them back and point to what they were doing (/session-start).
The flow (four steps — you orchestrate all of them)
① Hello + the one-sentence what-is-this (~20 sec)
Greet by asking their name/handle to use. Say, in one sentence, what this is:
"This is your own AI notebook-and-assistant that remembers everything and gets smarter about you over time. I'll set it up with you — takes about 15–20 minutes, and you can stop anytime."
Tell them the shape: "First I get to know you (a few questions), then I build your space, then you're live." Then start step ②. Don't wait for a long answer — keep momentum.
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.
- 2d ago First seen · 113 lines · 51 tokens per session scan A 6ffb916a22ea
start is a skill published in the GitHub repository xcota/pos (43 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,720 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 2026-08-30.
Other skills, from other repositories
capture-knowledge
将对话、项目文档、调试经验或用户指定材料沉淀到 Second Brain。用于“保存知识”“提取经验”“导入文档”“记录到知识库”“capture knowledge”等请求；先保存可追溯来源，再按一个稳定主题一张卡提取或更新 canonical 页面，禁止把 README、报告、故事或整段会话直接做成一张大卡。.
second-brain-learn
从当前 Agent 对话和工作轨迹中挖掘可长期保留的偏好、方法、Agent 角色事实、项目规则、知识与山脉进展；审计现有 owner，新增、纠错、缩限、替代、合并、迁移或退役规则，自动合并有证据的低风险变化，高风险变更先询问用户，并同步当前 Agent。用户说学习、记住、采纳或停止某种行为、修正规则、保存本次经验、从当前对话改进、运行 /learn，或要求未来 Agent 遵守某项教训时使用。.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
period-summary
Period summary (w/m/q/y) — reflect on the period, score it, close it out.
rtg-knowledge-graph-mcp
Operate the Vellis RTG Knowledge Graph MCP server for agent-driven graph work. Use when an agent has RTG MCP tools such as rtgvalidategraph, rtgapplylivegraphchanges, rtgstageknowledgechanges, rtgapplymigrationcutover, rtgexecutequery, snapshots, or ledger replay, especially for schema evolution, validation recovery…
engrama-onboard
Build a personalized Engrama memory graph for any user through a conversational interview. Use this skill whenever someone says "set up Engrama", "create my graph", "onboard", "build my profile", "configure Engrama for me", or asks how to start using Engrama. Also use when the user mentions they have a different role…