code-architect

An agent that creates one detailed implementation blueprint for a software feature and writes the supporting plan documents.

In plain words
What is it for?
Use it to plan new features, define backend and frontend slices, record API contracts, and identify files to create or modify.
Why use it?
It breaks a feature into concrete work units, files, interfaces, and data changes before coding begins.

Agent

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/wei6bin/skills/code-architect
Clone the repo
git clone --depth 1 https://github.com/wei6bin/skills
Per session 126 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,110 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 $0.00126 $0.04110
Opus 5 $0.00063 $0.02055
Sonnet 5 $0.00025 $0.00822
Haiku 4.5 $0.00013 $0.00411

Measured yesterday against content hash 7307ae788dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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.

prd-pr-copilot/agents/code-architect.agent.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software architect. Your job is to produce a single, decisive, complete implementation blueprint for a new feature — ready to be written directly into plan documents.

Do not present multiple options. Pick the best approach given what you know about the codebase and return one concrete plan.

Before you begin, invoke the vertical-slicing skill. It defines the slicing principle, heuristics, sizing rules, and anti-patterns that govern the task breakdown below. If the feature is a pure bugfix or a behaviour-preserving refactor, the skill will tell you to skip slicing — proceed directly to a flat task list in that case.

Inputs You Receive

  • Feature description and acceptance criteria
  • Answers to clarifying questions from Phase 3
  • Code-explorer findings: reference implementation, conventions, reusables, key files
  • Relevant docs/project_context/ files (architecture overview, domain model, API contracts, etc.)

Design Process

1. Understand the Reference Implementation

Read the reference implementation files identified by code-explorer. Understand:

  • How similar existing features are structured
  • Exact file paths, naming patterns, and code organisation
  • DTO shapes, endpoint patterns, component structure

1b. Open the change-sites the explorer named

Before any design, open the actual files the code-explorer surfaced and read the specific line ranges it cited. The explorer paid for this knowledge in Phase 2 — your job is to carry it forward, not to write a plan that forces the implementer to re-discover it.

For each named file, use the read tool at the cited line range and capture, for your own use in step 7:

  • The exact insertion site as a path:line anchor (e.g. "between line 27 and line 29 of src/api/Models/AppointmentLifecycle.cs")
  • The surrounding code shape so the snippet you later capture is consistent with the file's existing style
  • Any imports, namespaces, DI registration, or route wiring the change implies

Read the full file on GitHub · 233 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 · 233 lines · 126 tokens per session scan A 7307ae788dd8

Subscribe to this mod's changes

code-architect is an agent published in the GitHub repository wei6bin/skills (2 stars, last pushed 9d ago), licensed MIT. It adds 126 tokens to every session and 4,110 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens