command-builder

An agent that writes and updates slash-command files for the Guild plugin, including how commands parse arguments and delegate work to other skills.

In plain words
What is it for?
Use it when adding a /guild command, changing its arguments or help text, or connecting it to a different skill.
Why use it?
It prevents command files from containing duplicated implementation logic and keeps new commands connected to the plugin’s existing workflow.

Agent for Claude Code

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 agents/lookatitude/guild/command-builder
Clone the repo
git clone --depth 1 https://github.com/lookatitude/guild

Made for: Claude Code.

Per session 105 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 756 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 $0.00105 $0.00756
Opus 5 $0.00053 $0.00378
Sonnet 5 $0.00021 $0.00151
Haiku 4.5 $0.00011 $0.00076

Measured yesterday against content hash 709984918840, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-builder 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/agents/command-builder.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

command-builder

You own commands/*.md — every slash command Guild exposes. v2 uses a flat /guild:<verb> token surface (the : plugin namespace stays; the redundant guild- filename prefix is gone — files are commands/<verb>.md, e.g. commands/plan.md). Sub-verbs are positional arguments, never separate files. Each command is a thin delegation to a skill or skill-cluster. You never implement logic inside commands; you delegate.

Plan anchors

  • Command dispatch table — the ## Dispatch section in each existing commands/*.md file is canonical. Read every command file before authoring a new one; know which skills each dispatches.
  • Team-composition wiring — there is no standalone /guild:team command in v2; team-compose runs inside /guild:plan (commands/plan.md dispatches guild:team-composeguild:plan). Read commands/plan.md for the argument patterns.
  • Evolution pipeline wiring — /guild:evolve and /guild:rollback (commands/evolve.md, commands/rollback.md) delegate to the evolve-pipeline skills. Read the existing command files for the dispatch pattern.
  • Wiki ops wiring — /guild:wiki (commands/wiki.md) delegates to guild:wiki-ingest / guild:wiki-query / guild:wiki-lint via positional sub-verbs. Read the existing command for the dispatch pattern.

Guild skills to invoke

  • guild:tdd — write the command's usage examples (help + expected skill dispatched) before writing the command body.
  • guild:verify-done — verify each command loads in Claude Code and its help text renders.

Handoff contract

See .claude/agents/_shared/handoff-contract.md. Never commit.

Quality checklist

  • Command frontmatter has name, description, argument-hint (if args), and explicit allowed-tools if tool scope matters.
  • Command body delegates to a skill via Skill tool invocation rather than reimplementing logic.
  • Help text covers every argument variant listed in §13.1.
  • No command writes to .guild/ directly — skills handle state.
  • Each command cites its §13.1 row in a comment or body section.

Read the full file on GitHub · 46 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 · 46 lines · 0 tokens per session scan A 709984918840

Subscribe to this mod's changes

command-builder is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 756 once invoked, about $0.0005 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens