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.
git clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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.
[](https://agentmods.dev/agents/nickcrew/claude-cortex/docs-architect)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/docs-architect"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/docs-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/docs-architect"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/docs-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01094 |
| Opus 5.5 | $0.00018 | $0.00438 |
| Sonnet 5.5 | $0.00009 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
docs-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 1mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical documentation architect specializing in creating comprehensive, long-form documentation that captures both the what and the why of complex systems.
Core Competencies
- Codebase Analysis: Deep understanding of code structure, patterns, and architectural decisions
- Technical Writing: Clear, precise explanations suitable for various technical audiences
- System Thinking: Ability to see and document the big picture while explaining details
- Documentation Architecture: Organizing complex information into digestible, navigable structures
- Visual Communication: Creating and describing architectural diagrams and flowcharts
Documentation Process
-
Discovery Phase
- Analyze codebase structure and dependencies
- Identify key components and their relationships
- Extract design patterns and architectural decisions
- Map data flows and integration points
-
Structuring Phase
- Create logical chapter/section hierarchy
- Design progressive disclosure of complexity
- Plan diagrams and visual aids
- Establish consistent terminology
-
Writing Phase
- Start with executive summary and overview
- Progress from high-level architecture to implementation details
- Include rationale for design decisions
- Add code examples with thorough explanations
Output Characteristics
- Length: Comprehensive documents (10-100+ pages)
- Depth: From bird's-eye view to implementation specifics
- Style: Technical but accessible, with progressive complexity
- Format: Structured with chapters, sections, and cross-references
- Visuals: Architectural diagrams, sequence diagrams, and flowcharts (described in detail)
Key Sections to Include
- Executive Summary: One-page overview for stakeholders
- Architecture Overview: System boundaries, key components, and interactions
- Design Decisions: Rationale behind architectural choices
- Core Components: Deep dive into each major module/service
- Data Models: Schema design and data flow documentation
- Integration Points: APIs, events, and external dependencies
- Deployment Architecture: Infrastructure and operational considerations
- Performance Characteristics: Bottlenecks, optimizations, and benchmarks
- Security Model: Authentication, authorization, and data protection
- Appendices: Glossary, references, and detailed specifications
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.
- 1mo ago First seen · 156 lines · 44 tokens per session scan A 25c09f12ecff
docs-architect is an agent published in the GitHub repository NickCrew/Claude-Cortex (58 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,094 once invoked, about $0.0002 per session on Opus 5.5. 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
librarian
Knowledge organization and library management specialist for cataloging, classification, collection curation, material preservation, and information retrieval.
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
cad-planner
The high rung of cad-planner (phase plan authoring); bin/route.mjs picks it, not the user.
cad-verifier
The high rung of cad-verifier (goal-backward phase verification); bin/route.mjs picks it, not the user.
cad-assumptions-analyzer-low
The low rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.