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/yc-software/qm/onboardingnpx skills add yc-software/qm --skill onboardinggit clone --depth 1 https://github.com/yc-software/qmWhat 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 | $0.00024 | $0.01157 |
| Opus 5 | $0.00012 | $0.00579 |
| Sonnet 5 | $0.00005 | $0.00231 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
onboarding scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS -X POST "$AGENT_API_URL/v1/connectors/oauth/consent/mint" \ How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding
Use this skill when onboarding is pending or the user asks to onboard again. Finish with their tools connected, a durable profile, and one or two useful automations proposed or running. Keep turns short and conversational, but complete the steps in order unless the user explicitly asks to skip one:
- Offer the app connections configured by the admin.
- Choose how you should sound.
- Read connected tools for a real work snapshot.
- Confirm your read, then propose and—with approval—create concrete help.
If they ask to stop, mark onboarding completed and do not raise it again. A returning user keeps what memory already knows; focus on what changed.
State and persistence
Memory is the source of truth. Before the first question, read the notebook with the
memory tool and rewrite it with an ## Onboarding section and this exact marker:
- Onboarding: pending v2 since YYYY-MM-DD.
After every step, read and rewrite the full notebook, preserving existing content. Record connected apps, focus areas, people and aliases, deadlines, rules, recurring workflows, cron IDs, and published app links. On completion or an explicit stop, replace the marker with:
- Onboarding: completed v2 on YYYY-MM-DD.
Memory is not a file; never edit it with shell commands.
1. Connect accounts
The surface already authenticated the user. Greet them by name; do not ask their name or role, and do not research them in the opening turn. Explain that connecting lets you act as them without seeing their password and can be revoked.
Read the live Connected apps block. Offer only providers it says were configured by the
admin. If it says none are enabled, skip this step without naming or suggesting
other providers. The greeting and capability examples must follow that same allowlist:
do not advertise, name, ask about, or promise a provider that is not listed. Otherwise
ask which available services they use, mint links only for those choices, and present
the returned connectUrl values together:
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.
- 3d ago First seen · 115 lines · 24 tokens per session scan A 15ec15cc961b
onboarding is a skill published in the GitHub repository yc-software/qm (14,428 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,157 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
address-feedback
Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).