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 xonika9/agent-skills --skill x9-onboardinggit clone --depth 1 https://github.com/xonika9/agent-skillsWrote 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/xonika9/agent-skills/x9-onboarding)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-onboarding"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-onboarding/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/xonika9/agent-skills/x9-onboarding"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-onboarding.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 | $0.00097 | $0.01084 |
| Opus 5 | $0.00048 | $0.00542 |
| Sonnet 5 | $0.00019 | $0.00217 |
| Haiku 4.5 | $0.00010 | $0.00108 |
Grade A, and why
x9-onboarding 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 10d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X9 onboarding
Check only the user-named x9-* skills, or use the current runtime's active skill
catalog when the user did not name targets. Resolve every selected skill's physical path
against this loaded skill's package skills root. Read a declaration only when its
resolved path remains below that root; never read an external path or symlink target.
Report an untrusted target as PARTIAL and BLOCKED with that reason. If neither an
explicit target nor a safe active catalog is available, report scope as PARTIAL and
BLOCKED and ask for skill names rather than scanning directories.
Read the declaration contract for trusted
references/onboarding.json data. A missing declaration means that skill has no
declared external requirements or runtime restriction: report COMPLETE and READY; never infer a requirement
from prose. An unreadable or invalid declaration is PARTIAL and BLOCKED; report only
its package-relative source and contract failure, not its contents. If the current runtime
is absent from supported_runtimes, report COMPLETE and BLOCKED before requirement
filtering; this is an explicit compatibility fact, not missing evidence. Otherwise filter a declaration
to the current runtime before checking it. Use the current runtime adapter for live facts:
OpenCode, Claude Code, or
Codex.
Status model
Keep coverage and readiness as separate columns. For an individual requirement,
COMPLETE means a supported passive check returned a safe present or absent fact;
PARTIAL means a required fact could not be safely established; EXPLICIT is reserved
for manual. manual always returns EXPLICIT and USER_ACTION. A present passive
fact is READY; an absent supported prerequisite is NEEDS_SETUP; unavailable or unsafe
evidence is BLOCKED. Return PENDING_RESTART only when the adapter safely observes the
configured component and also observes that this session lacks it; do not infer it from a
missing capability.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 72 lines · 97 tokens per session scan A 3a6cded02a84
x9-onboarding is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 97 tokens to every session and 1,084 once invoked, about $0.0005 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
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
aria
Designs the data model, API contracts, and structural foundation of the system.
api-security
Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs: discovery, authentication and authorization flaws (BOLA/IDOR, JWT/OAuth), rate-limit testing, and a structured multi-phase methodology.