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 agents/lookatitude/guild/command-buildergit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00105 | $0.00756 |
| Opus 5 | $0.00053 | $0.00378 |
| Sonnet 5 | $0.00021 | $0.00151 |
| Haiku 4.5 | $0.00011 | $0.00076 |
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.
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
## Dispatchsection in each existingcommands/*.mdfile is canonical. Read every command file before authoring a new one; know which skills each dispatches. - Team-composition wiring — there is no standalone
/guild:teamcommand in v2; team-compose runs inside/guild:plan(commands/plan.mddispatchesguild:team-compose→guild:plan). Readcommands/plan.mdfor the argument patterns. - Evolution pipeline wiring —
/guild:evolveand/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 toguild:wiki-ingest/guild:wiki-query/guild:wiki-lintvia 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 explicitallowed-toolsif tool scope matters. - Command body delegates to a skill via
Skilltool 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.
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.
- yesterday First seen · 46 lines · 0 tokens per session scan A 709984918840
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.