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 skills/matrixfounder/agentic-development/architecture-formatnpx skills add MatrixFounder/Agentic-development --skill architecture-formatgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWrote 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/skills/matrixfounder/agentic-development/architecture-format)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/architecture-format"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/architecture-format.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.02530 |
| Opus 5 | $0.00010 | $0.01265 |
| Sonnet 5 | $0.00004 | $0.00506 |
| Haiku 4.5 | $0.00002 | $0.00253 |
Grade A, and why
architecture-format 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 today.
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 — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Document Structure
Your architecture must contain the following sections:
1. Task Description
Link to TASK and brief summary of requirements
2. Functional Architecture
Description of the system in terms of functions it performs.
2.1. Functional Components
For each functional component describe:
Component Name: [Example, "User Management"]
Purpose: [Why this component is needed]
Functions:
-
Function 1: [Description]
- Input: [what accepts]
- Output: [what returns]
- Related Use Cases: [UC-01, UC-03]
-
Function 2: [Description]
- Input: [what accepts]
- Output: [what returns]
- Related Use Cases: [UC-02]
Dependencies:
- Depends on which other components
- Which components depend on it
2.2. Functional Components Diagram
[Mermaid diagram showing connections between components]
3. System Architecture
Description of the system in terms of physical/logical components.
3.1. Architectural Style
Which architectural pattern is used:
- Monolith
- Microservices
- Layered Architecture
- Event-driven
- Etc.
Justification: [Why this style was chosen]
3.2. System Components
For each system component describe:
Component Name: [Example, "User Service"]
Type: [Backend service / Frontend / Database / Message Queue / etc.]
Purpose: [Why needed]
Implemented Functions: [Links to functions from functional architecture]
Technologies: [Programming language, frameworks]
Interfaces:
- Inbound: [Who and how accesses this component]
- Outbound: [Who and how this component accesses]
Dependencies:
- External libraries
- Other system components
- External services
3.3. Components Diagram
[Mermaid diagram showing components and their interaction]
4. Data Model
Description of data structure in the system.
4.1. Conceptual Data Model
Description of main entities and their relationships at a high level.
Entities:
Entity: [Name, e.g., "User"]
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.
- today First seen · 523 lines · 19 tokens per session scan A fca6a21fc108
architecture-format is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 2,530 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
Learn what defines effective BDD scenarios
Interactive guidance on writing complete, effective BDD scenarios for story-flow.
add-tests
Generates tests for existing code. Analyzes the target function, method, or class to identify the happy path, error cases, and edge cases, then writes test cases following the project's testing framework and naming conventions. Invoked when the user asks to add tests, write tests, cover code, or increase coverage.
tdd-implementation
Use when implementing any code change for a task – new behavior, a bugfix, or a revision after review – before writing the production code. Defines the failing-test-first cycle, public-seam testing, vertical slices, scaffold and infra handling, and counters to common excuses for tests-after-code.
test-writer
Writes tests that fail before a fix and pass after it.
test-generation
Generate and run unit/integration tests TDD-style across Python, Node, and .NET. Use when adding tests to untested code, implementing a feature test-first, or finding coverage gaps.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…