Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/me2resh/apexyardnpx agentmods add skills/me2resh/apexyard/onboardWrote 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/me2resh/apexyard/onboard)<a href="https://agentmods.dev/skills/me2resh/apexyard/onboard"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/onboard/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/me2resh/apexyard/onboard"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Tool Misuse · line 441 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00043 | $0.05637 |
| Opus 5.5 | $0.00017 | $0.02255 |
| Sonnet 5.5 | $0.00009 | $0.01127 |
| Haiku 4.5 | $0.00004 | $0.00564 |
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 15d 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 — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.
/onboard — Guided First-Run Onboarding
This is increment 1 of the guided-onboarding walking skeleton (technical
design: docs/technical-designs/onboarding-increment-1.md, ticket #910),
now layered with increment 2's depth adaptivity (technical design:
docs/technical-designs/onboarding-increment-2.md § D2/D7, ticket #914).
/onboard is a thin orchestrator + router, not a replacement for
/setup or /handover — it sequences those two skills (plus /feature)
behind a capability tour and an explicit branch. It never edits /setup,
/handover, or /feature; their direct and scripted behaviour stays
byte-for-byte unchanged (see AgDR-0097).
This flow now renders in one of two depth modes — terse or guided
— off a single shared session marker, not a forked skill (US-5/FR-6).
Terse renders every step exactly as increment 1 did (byte-for-byte
identical output — NFR Backward-compat). Guided adds one short
"why this matters" framing sentence after each major step. Depth mode
changes only explanatory narration — it never changes which gate
fires, which approval is required, or any role boundary (the
"presentation only" invariant, mechanically guarded by
.claude/hooks/tests/test_depth_mode.sh's invariant case). See Step 3.5
below for derivation, and "Depth mode override + transparency" for the
mid-session override (FR-6) and the "what mode am I in?" affordance
(FR-9).
The per-term teach-in-context glossary + just-in-time asides (#913) are
now wired into this flow. In guided mode, the first time this skill
uses one of the five core terms — issue/ticket, PR, merge, branch, CI —
toward the adopter, it weaves in a short inline parenthetical explaining
it, once per term per session (design § D3). See "Just-in-time glossary
asides" below for the mechanism. Terse mode sees zero asides — this is
structural, not a formatting choice (the same $mode gate Step 3.5
derives). The ambient any-session lookup + full /tutorial glossary
render (#915) is still a sibling ticket, not yet built as of this
ticket — asking "what's a merge?" outside a guided /onboard run isn't
wired up yet.
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.
- 15d ago Changed · +6 lines d27c68e33bc7
- 22d ago Changed · +2 lines 82073f37d6e4
- 29d ago Changed · +9 lines 3a4133dec7ee
- 1mo ago Changed · +14 lines 44a83556e9cd
- 1mo ago Changed · +4 lines e8ad2dcd462d
- 2mo ago First seen · 491 lines · 43 tokens per session scan A f78fb99524ee
onboard is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 5,637 once invoked, about $0.0002 per session on Opus 5.5. 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.
onboard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onboardme2resh/apexyard | Skill | 542 | yesterday | MIT | A | 43 | Claude Code |
| great_ctoavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 32 | Claude Code |
| skeptical-triageavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 49 | Claude Code |
| product-economicsavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 55 | Claude Code |
| cost-modelavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 59 | Claude Code |
| migration-ready-schemaavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 133 | Claude Code |
| pm-planningavelikiy/great_cto | Skill | 112 | 2d ago | MIT | A | 57 | Claude Code |