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/lookatitude/guild/learn-onboardnpx skills add lookatitude/guild --skill learn-onboardgit clone --depth 1 https://github.com/lookatitude/guildWrote 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/lookatitude/guild/learn-onboard)<a href="https://agentmods.dev/skills/lookatitude/guild/learn-onboard"><img src="https://agentmods.dev/badge/skills/lookatitude/guild/learn-onboard.svg" alt="Measured on agentmods" 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 | $0.00191 | $0.02969 |
| Opus 5 | $0.00096 | $0.01484 |
| Sonnet 5 | $0.00038 | $0.00594 |
| Haiku 4.5 | $0.00019 | $0.00297 |
Grade A, and why
guild-learn-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 5d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use it
Use to turn the deterministic tour skeleton (produced by build-tour.ts,
stage 6) into the human-readable
OnboardingTour artifact and an onboarding guide. The script fixes the
dependency-BFS step order; this skill writes the narration +
languageLesson the spec assigns to the LLM half, and assembles the guide a
new contributor reads first.
When not to use it
Not for building the graph (guild:learn-graph owns stages 2–7). Not for
re-ordering tour steps — the BFS order is deterministic and LOCKED; this skill
narrates, it does not re-sequence. Not for the cheap-scan map
(guild:learn-map), the per-run diff (guild:learn-diff), or a single
file/module explanation (guild:learn-explain). Not for querying the graph
(kg-query via guild:context-assemble / guild:wiki-query). Not required
for Init — it is part of the lazy, gated deep tier.
Required inputs
.guild/indexes/knowledge-graph.json(guild.knowledge_graph.v1orguild.knowledge_graph.v2— both carry the sametour[]/node contract this skill consumes) with a populatedtour[]skeleton frombuild-tour.ts. At a project root, iftour[]is empty or the graph is absent, escalate — do not invent a tour from raw files. At a detected workspace root (strict detection in §"Workspace-root fallback"), an emptytour[]is by-design and that section governs instead of this bullet.- The graph's
layers[],nodes[], and persisteddomain/componentlabels — narration is grounded in the graph, never re-read source. OnboardingTouris a frozen Markdown artifact (no JSON schema); its shape is defined in the§ Output formatsection below. The output-locations table is owned byguild:learn-map.
Output format
.guild/indexes/onboarding-tour.md— theOnboardingTour: 5–15 ordered steps, each withtitle, a pedagogicaldescription,nodeIds(1–5 per step — from the skeleton, order preserved, at project roots; at a detected workspace root, the hand-selected graph node ids per §"Workspace-root fallback", recorded explicitly per step), and an optionallanguageLesson(a short teaching note about a language/framework idiom the step's nodes exemplify).- A derived onboarding guide section (same file or a sibling synthesised
view): what the project is (from
KnowledgeGraph.project.description), the layer map, the primary Domain→Flow→Step paths, and "start here" pointers. - Copy to
docs/ONBOARDING.mdonly on explicit user request — never silently.
What ships with it
2 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.
- 5d ago First seen · 200 lines · 191 tokens per session scan A 7a6ac24490db
guild-learn-onboard is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 5d ago), licensed MIT. It adds 191 tokens to every session and 2,969 once invoked, about $0.0010 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.