guild-specialize

A project-exploration guide that fills a Guild agent configuration with the real technology stack, architecture, and coding conventions.

In plain words
What is it for?
Run it after guild init, after adding a major technology, or after the project structure changes substantially.
Why use it?
It replaces generic setup notes and placeholders with information gathered from the project itself.

Skill for Claude CodeCodex

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/guild-agents/guild/guild-specialize
Any agent
npx skills add Guild-Agents/guild --skill guild-specialize
Clone the repo
git clone --depth 1 https://github.com/Guild-Agents/guild

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,836 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 $0.00022 $0.01836
Opus 5 $0.00011 $0.00918
Sonnet 5 $0.00004 $0.00367
Haiku 4.5 $0.00002 $0.00184

Measured yesterday against content hash d7d9a3ba123a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guild-specialize 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.

.claude/skills/guild-specialize/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guild Specialize

Explores the user's real project and enriches the entire Guild configuration with concrete information about the detected stack, architecture, and conventions.

This skill runs once after guild init. It transforms generic placeholders into real project information.

When to use

  • Immediately after running guild init
  • When a new stack is added to the project (new database, new framework)
  • When the project structure has changed significantly

Process

Step 1 — Read base context

Read the Guild configuration files:

  • CLAUDE.md — current instructions (contains [PENDING: guild-specialize] placeholders)
  • PROJECT.md — identity and stack declared during init

Step 2 — Explore the real project

Investigate the real project structure looking for:

Dependencies and versions:

  • package.json (Node.js/frontend)
  • pom.xml or build.gradle (Java)
  • requirements.txt or pyproject.toml (Python)
  • Gemfile (Ruby)
  • go.mod (Go)
  • Cargo.toml (Rust)

Architecture and structure:

  • Folders src/, app/, lib/, pkg/, internal/
  • Organization pattern: by layers, by features, by domain
  • Project entry points

Configuration and conventions:

  • tsconfig.json, eslint.config.*, .prettierrc
  • .env.example, .env.local (environment variables — do NOT read real .env)
  • Dockerfile, docker-compose.yml
  • CI/CD: .github/workflows/, .gitlab-ci.yml

Database and migrations:

  • Folder migrations/, db/, prisma/, drizzle/
  • Configured ORM or query builder
  • Existing schema

Existing documentation:

  • README.md — project overview
  • Internal documentation in docs/

Step 3 — Enrich CLAUDE.md

Invoke the Tech Lead agent using Task tool with model: "opus" (reasoning tier) to replace all [PENDING: guild-specialize] placeholders in CLAUDE.md with real information:

  • Stack with exact versions: extracted from dependency files
  • Folder structure explained: what each main folder does
  • Detected code conventions: linter, formatter, import style
  • Identified architecture patterns: MVC, hexagonal, modular, etc.
  • Known environment variables: listed from .env.example
  • Visible limitations and technical debt: outdated dependencies, TODOs found
  • Useful project commands: detected npm/make/cargo scripts

Read the full file on GitHub · 212 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 · 212 lines · 22 tokens per session scan A d7d9a3ba123a

Subscribe to this mod's changes

guild-specialize is a skill published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,836 once invoked, about $0.0001 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

codebase-memory

Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…

narumiruna/pi-extensions · 98 tokens

using-pi-subagents

Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.

narumiruna/pi-extensions · 54 tokens

herdr

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires…

narumiruna/pi-extensions · 74 tokens

laravel-actions

Build, refactor, and troubleshoot Laravel Actions using lorisleiva/laravel-actions. Use when implementing reusable action classes (object/controller/job/listener/command), converting service classes/controllers/jobs into actions, orchestrating workflows via faked actions, or debugging action entrypoints and wiring.

coollabsio/coolify · 62 tokens

debugging-output-and-previewing-html-using-ray

Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.

coollabsio/coolify · 58 tokens

Shade dropdown surface contract

DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.

TryGhost/Ghost · 54 tokens