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/xyruscode/ai-sync/onboardnpx skills add XyrusCode/ai-sync --skill onboardgit clone --depth 1 https://github.com/XyrusCode/ai-syncWhat 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 | $0.00033 | $0.02658 |
| Opus 5 | $0.00016 | $0.01329 |
| Sonnet 5 | $0.00007 | $0.00532 |
| Haiku 4.5 | $0.00003 | $0.00266 |
Grade A, and why
onboard 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard
Use this skill only when the user explicitly invokes /onboard.
Goal: run a lightweight onboarding interview and produce a handoff. Do not execute setup work.
Hard Rules
- Ask one question at a time.
- Only use tools listed in Tool Boundary.
- Do not inspect files, browse MCP descriptors, read local paths, move workspaces, clone repositories, open UI, configure MCP servers, install plugins, or change settings.
- If the user asks to take an action outside Tool Boundary, end onboarding and give them the exact next prompt/action to run outside this skill.
- If the user asks a normal Cursor question, answer it directly, then ask whether to continue onboarding or stop.
- If the user seems done, stop the onboarding flow.
- After onboarding ends, stop applying this skill's Tool Boundary and handle future user messages normally unless the user invokes
/onboardagain. - Your output is usually a handoff, not execution. The only exceptions are the allowed memory save and final Plan mode switch.
- Prefer the standard flow, but do not make the user repeat information they already gave. Acknowledge early answers and continue from the next useful step.
- Keep each turn focused. Do not repeat the same question, prose paragraph, or tool call in the same turn.
Tool Boundary
During onboarding, only these tools are allowed:
AskQuestion: use for fixed-choice questions.cursor_dialog: use only after collecting both name and work context to save them to a personal rule. Ifcursor_dialogis exposed through thecursor-app-controlMCP call tool, callcursor-app-control->cursor_dialogdirectly with the exact rule arguments below. Run the memory-save flow before continuing unless the user already clearly asked not to save onboarding details.SwitchMode: use only at the final handoff, and only if the user explicitly agrees to continue in Plan mode. If the user agrees, you must callSwitchModewithtarget_mode_id: "plan".
Do not use any other tools. In particular, do not use shell, file read/search, MCP descriptor browsing, non-cursor_dialog MCP tools, get_cursor_user_state, workspace moves, repo clones, settings changes, automation UI, or project inspection.
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 · 177 lines · 33 tokens per session scan A ad68425f9ae8
onboard is a skill published in the GitHub repository XyrusCode/ai-sync (2 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 2,658 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…