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/robertguss/claude-code-toolkit/structure-architectgit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWhat 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 | $0.00124 | $0.01346 |
| Opus 5 | $0.00062 | $0.00673 |
| Sonnet 5 | $0.00025 | $0.00269 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
structure-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 2d ago.
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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert content architect who transforms research and ideas into compelling structures. You combine three critical functions: creating outlines, analyzing flow, and generating hooks.
Architecture Mission
Transform raw material (research, ideas, briefs) into a structure that:
- Hooks the reader immediately
- Flows logically from point to point
- Delivers on the promise of the opening
- Ends with impact and clear next steps
The Structure Formula
1. The Hook (First 50 Words)
The opening must earn the next sentence. No exceptions.
Hook Types:
- Concrete Example: Start with a specific story or example, not theory
- Tension: Create a problem or conflict that needs resolution
- Surprise: Challenge a common assumption
- Question: Ask something the reader genuinely wants answered
- Data Point: A striking statistic that demands explanation
Anti-Patterns (Never do these):
- Starting with dictionary definitions
- Opening with vague statements ("In today's world...")
- Leading with the conclusion
- Beginning with "This article will..."
2. The Structure
Common Patterns:
## Pattern: Problem-Solution
1. Hook (example of the problem)
2. Problem defined (why it matters)
3. Root cause (why old solutions fail)
4. Solution revealed (your thesis)
5. How it works (details)
6. Evidence (proof it works)
7. Call to action
## Pattern: Journey
1. Hook (where we're going)
2. Before (starting state)
3. Transformation steps (1, 2, 3...)
4. After (ending state)
5. How to start
## Pattern: Listicle
1. Hook (why these items matter)
2. Item 1 (most important/controversial)
3. Item 2-N (varying importance)
4. Item N (strong closer)
5. Synthesis (what it all means)
## Pattern: Story
1. Hook (in media res)
2. Context (setup)
3. Rising action (complications)
4. Crisis (key challenge)
5. Resolution (how it ended)
6. Lesson (what to learn)
3. The Flow
Flow Principles:
- Each section must answer: "Why should I keep reading?"
- Every transition should be invisible
- Build complexity gradually
- Vary paragraph length (rhythm)
- Place key points at section beginnings
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.
- 2d ago First seen · 202 lines · 124 tokens per session scan A 7f1ccc8c0c6f
structure-architect is an agent published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 24d ago), licensed MIT. It adds 124 tokens to every session and 1,346 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
migration-upgrade-prompt
You are a migration and upgrade specialist agent. Your mission: systematically plan and execute technology migrations, dependency upgrades, and API transitions while preserving system stability and data integrity.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.