init

A project setup command that creates local project knowledge, including a wiki and a basic map of an existing codebase; it can optionally run deeper learning.

In plain words
What is it for?
Use it to onboard an existing repository, scaffold knowledge for a new product, or request the full learning pipeline.
Why use it?
It gives an unfamiliar repository a documented starting point before development begins.

Command

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 commands/lookatitude/guild/init
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,016 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 $0.00067 $0.03016
Opus 5 $0.00034 $0.01508
Sonnet 5 $0.00013 $0.00603
Haiku 4.5 $0.00007 $0.00302

Measured yesterday against content hash f2b6aa167731, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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.

commands/init.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/guild:init — phase: Init

The Init phase entrypoint. Onboards an existing repo or scaffolds new-product knowledge: builds the wiki and, for a brownfield repo, the cheap scan tier only — the derived CodebaseMap plus a confidence-tagged architecture-map.md stub. That pair is Init-DONE. The deep semantic KnowledgeGraph + onboarding tour are lazy, gated by the --learn flag or defaults.auto_learn: true config — built via the learn-* pipeline (same skills as /guild:learn), not produced at Init by default.

Verb↔phase edge: /guild:init → Init. Phase concept binding: lifecycle/phase-entrypoints.md · lifecycle/lifecycle-overview.md (one state machine, six phase entrypoints).

Contract binding

Before any producer work begins, this phase resolves the frozen guild.phase_entry.v1 contract (review.learning_checkpoint: true). The Tier-2 defaults: config folded at intake is controlled by P1-config-001 — see /guild:config for the schema.

Usage

/guild:init
/guild:init --learn
/guild:init --new

All five global flags + --dry-run apply.

Args & local flags

  • Args: — (no positional)
  • Local flags:
    • --learn — run the full learn-* pipeline now (guild:learn-map / learn-graph / learn-knowledge (cost-gated knowledge tier) / learn-onboard / learn-diff / learn-explain), the same skills /guild:learn invokes. Also triggered automatically when defaults.auto_learn: true is set in .guild/settings.json. Folds in the former --deep-scan flag (D3).
    • --new — force the new-product scaffold path.

Gates (default)

  • New-product Q&A I
  • G-init review A

Note: --learn and defaults.auto_learn: true both run the full learn-* pipeline without an extra gate (explicitly requested). The former ask-before-deep-scan interactive gate is removed (D3).

Output artifact

.guild/guild.yaml, .guild/init/<slug>.md, .guild/wiki/**, .guild/raw/**, .guild/settings.json (the project config surface, scaffolded fully-documented if absent — see below), and (brownfield, cheap scan tier = Init-DONE) .guild/indexes/codebase-map.json + confidence-tagged wiki/concepts/architecture-map.md stub. knowledge-graph.json + onboarding-tour.md are deferred — lazy, produced only under --learn / defaults.auto_learn by the learn-* pipeline, never at Init by default.

Read the full file on GitHub · 244 lines

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. yesterday First seen · 244 lines · 67 tokens per session scan A f2b6aa167731

Subscribe to this mod's changes

init is a command published in the GitHub repository lookatitude/guild (7 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 3,016 once invoked, about $0.0003 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.