guild-learn-onboard

guild-learn-onboard is a skill for Claude Code from lookatitude/guild. It costs 191 tokens per session (2,969 once invoked), scanned A, original, MIT.

A narrator that turns a dependency-ordered code tour into a written onboarding guide. The dependency order shows what a new contributor should understand first based on what code depends on what.

In plain words
What is it for?
Use it when a populated knowledge graph already contains a tour outline. It writes the narration and guide but does not build or reorder the tour.
Why use it?
It adds explanations and teaching notes to an automatically ordered tour, making the project easier for a new contributor to learn.

Skill for Claude Code

Written for Claude Code: when-to-use in frontmatter.

Part of the guild plugin — 114 skills, 23 commands, 14 agents, 10 hooks, 2 MCP servers shipped together

Install

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.

agentmods
npx agentmods add skills/lookatitude/guild/learn-onboard
Any agent
npx skills add lookatitude/guild --skill learn-onboard
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild

Made for: Claude Code.

Or install guild, the plugin that ships this one along with the rest of its 114 skills, 23 commands, 14 agents, 10 hooks, 2 MCP servers.

Wrote 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.

agentmods badge for guild-learn-onboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/lookatitude/guild/learn-onboard.svg)](https://agentmods.dev/skills/lookatitude/guild/learn-onboard)
Your own site
<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>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 7a6ac24490db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

skills/knowledge/learn-onboard/SKILL.md · 200 lines

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.v1 or guild.knowledge_graph.v2 — both carry the same tour[]/node contract this skill consumes) with a populated tour[] skeleton from build-tour.ts. At a project root, if tour[] 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 empty tour[] is by-design and that section governs instead of this bullet.
  • The graph's layers[], nodes[], and persisted domain/component labels — narration is grounded in the graph, never re-read source.
  • OnboardingTour is a frozen Markdown artifact (no JSON schema); its shape is defined in the § Output format section below. The output-locations table is owned by guild:learn-map.

Output format

  • .guild/indexes/onboarding-tour.md — the OnboardingTour: 5–15 ordered steps, each with title, a pedagogical description, 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 optional languageLesson (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.md only on explicit user request — never silently.

Read the full file on GitHub · 200 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 200 lines · 191 tokens per session scan A 7a6ac24490db

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories