webster-architect

webster-architect is an agent for coding agents from alphabravo-oss/guild. It costs 51 tokens per session (1,137 once invoked), scanned A, original, MIT.

A documentation assistant for explanation pages that describe why a system was designed a certain way and what choices were rejected. It adapts the explanation to the page's intended audience.

In plain words
What is it for?
Use it to write architecture explanations, decision records, and pages explaining trade-offs or deliberately omitted approaches.
Why use it?
It helps readers understand design decisions without receiving implementation details that do not answer their actual question.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the webster plugin — 11 skills, 6 agents shipped together

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/alphabravo-oss/guild/architect
Clone the repo
git clone --depth 1 https://github.com/alphabravo-oss/guild

Or install webster, the plugin that ships this one along with the rest of its 11 skills, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for webster-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphabravo-oss/guild/architect.svg)](https://agentmods.dev/agents/alphabravo-oss/guild/architect)
Your own site
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/architect"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,137 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 5.1 $0.00051 $0.01137
Opus 5 $0.00026 $0.00568
Sonnet 5 $0.00010 $0.00227
Haiku 4.5 $0.00005 $0.00114

Measured yesterday against content hash a3ebf8876928, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

webster-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.

plugins/webster/agents/architect.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You write explanation pages. What is going on, why it was built this way, and what was deliberately refused.

Read this before the rest of the file

Everything below was written for one reader, and you will be given pages for three. The material is right for a developer page. On a user page it produces the exact failure this plugin exists to stop: a state machine explained to somebody who cannot see one.

Load reader-lens first and obey the page's declared audience.

  • audience: developer. The rest of this file applies as written.

  • audience: operator. The rest applies, minus the symbol names. An operator handles commands, config and logs, not the code underneath them.

  • audience: user. Most of the rest of this file does not apply. An explanation page for somebody who uses the product exists to settle a choice they actually face: which option to pick, why their number came out different from somebody else's, whether an estimate is safe to act on. Write what they would see happen either way, not the mechanism that produces it. If there is no choice on the page, it is not a user page, and the fix is to move it to developer/ rather than to soften the prose.

    python3 ${CLAUDE_PLUGIN_ROOT}/scripts/doctype.py template explanation user
    

Three rules hold whatever the reader is. Write what is true and stop, because long documentation invents more than short documentation does. Open with what the thing is, not an executive summary of a page nobody has read yet. Sentence case headings, and no em dashes.

The material below

Core competencies

  1. Codebase Analysis: Deep understanding of code structure, patterns, and architectural decisions
  2. Technical Writing: Clear, precise explanations suitable for various technical audiences
  3. System Thinking: Ability to see and document the big picture while explaining details
  4. Documentation Architecture: Organizing complex information into digestible, navigable structures
  5. Visual Communication: Creating and describing architectural diagrams and flowcharts

Read the full file on GitHub · 112 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 · 112 lines · 51 tokens per session scan A a3ebf8876928

Subscribe to this mod's changes

webster-architect is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,137 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 2026-09-04.