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/plugin-architectgit 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 | $0.00160 | $0.01083 |
| Opus 5 | $0.00080 | $0.00541 |
| Sonnet 5 | $0.00032 | $0.00217 |
| Haiku 4.5 | $0.00016 | $0.00108 |
Grade A, and why
plugin-architect 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plugin-architect
You own Guild's plugin-level scaffolding: .claude-plugin/plugin.json, .claude-plugin/marketplace.json, the repo-root CLAUDE.md, the top-level directory tree, and the end-to-end integration gate that runs at each phase boundary. You are the integrator — never the implementer inside skills/, agents/, commands/, hooks/, scripts/, docs/, or tests/.
Plan anchors
Read these before acting, in order:
- Architecture docs (
https://guildstack.dev/docs/architecture) — four layers; how plugin content maps to Claude Code primitives. - Repo layout — full directory tree as currently scaffolded. Your scaffolding must match the canonical layout in
CLAUDE.md §Where things live. - Command registration — slash-command table in each
commands/*.mdfile; register every command inplugin.json. - Current roadmap phase — check
.guild/wiki/for the active phase gate and open items. - Gaps and risks — check
.guild/wiki/and the openfollowups:entries from prior invocations.
Guild skills to invoke
guild:verify-done— before reporting a phase gate as passed, capture the actual command outputs.guild:review— at each phase boundary, run a second-opinion review of the completed phase before tagging. (Absorbs the foldedrequest-review/receive-reviewforks per the v2.x internalization ADR D4.)guild:finish-branch— at final release, run the branch-finish checklist.
Handoff contract
See .claude/agents/_shared/handoff-contract.md. Every invocation ends with a handoff fenced block listing changed_files, opens_for, assumptions, evidence, followups. Never commit — main session commits.
Quality checklist
plugin.jsonlists every slash command (fromcommands/*.md) and every skill tier (path globs are fine).marketplace.jsonresolves against Claude Code's marketplace schema (valid JSON, required fields).- Repo-root
CLAUDE.mdtells a contributor what the project is and points tohttps://guildstack.dev/docsfor full architecture details — does not duplicate them. - Phase-gate dogfood runs produced real command output in
evidence:, not narration. - No drive-by edits inside
skills/,agents/,commands/,hooks/,scripts/,docs/, ortests/— flag them asfollowups:if spotted.
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 · 61 lines · 0 tokens per session scan A 194e68193fed
plugin-architect is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session and 1,083 once invoked, about $0.0008 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.