architecture

architecture is a skill for Claude Code from AbdurRafay2004/handoff. It costs 94 tokens per session (1,316 once invoked), scanned A, original, MIT.

A codebase review that looks for architectural friction and suggests focused improvements. Software architecture is the way a codebase is divided and how its parts depend on one another.

In plain words
What is it for?
Use it to identify candidate refactors, evaluate troublesome modules, and turn a chosen improvement into a decision and implementation plan.
Why use it?
It helps explain why code is difficult to change, navigate, or test and avoids jumping straight to a large rewrite. It can also revisit areas where repeated fixes suggest a deeper design problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the handoff plugin — 15 skills, 3 hooks 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 skills/abdurrafay2004/handoff/architecture
Any agent
npx skills add AbdurRafay2004/handoff --skill architecture
Clone the repo
git clone --depth 1 https://github.com/AbdurRafay2004/handoff

Made for: Claude Code.

Or install handoff, the plugin that ships this one along with the rest of its 15 skills, 3 hooks.

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 architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/abdurrafay2004/handoff/architecture.svg)](https://agentmods.dev/skills/abdurrafay2004/handoff/architecture)
Your own site
<a href="https://agentmods.dev/skills/abdurrafay2004/handoff/architecture"><img src="https://agentmods.dev/badge/skills/abdurrafay2004/handoff/architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 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 $0.00094 $0.01316
Opus 5 $0.00047 $0.00658
Sonnet 5 $0.00019 $0.00263
Haiku 4.5 $0.00009 $0.00132

Measured 6d ago against content hash e9546134f068, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architecture 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 6d 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.

skills/architecture/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture

Part of the Plan/Build phases — see the workflow skill for tiers and sequencing.

Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is leverage, locality, and testability. This is inherently T2/T3 work: the outcome is a decision and a plan, executed via the plan skill — never an immediate rewrite.

Two entry points

  1. Proactive — the user asks to improve the architecture, or asks why this codebase is painful to change, navigate, or test.
  2. Reactive — the debug skill hands off here under its rule that 3+ failed fixes on the same bug signals an architectural problem. Start the friction scan in the neighbourhood of the failed fixes.

Vocabulary and prior decisions

  • Use the design skill's glossary exactly — module, interface, depth, seam, leverage, locality — in every suggestion. Don't drift into "component," "service," "API," or "boundary."
  • Read the project's domain glossary and context notes in .handoff/context/ and any ADRs in docs/adr/ before scanning. Domain language names good seams; ADRs record decisions this skill should not re-litigate.
  • Name things in domain terms: if the glossary defines "Order," talk about "the Order intake module" — not "the FooBarHandler."

Process

1. Friction scan

Walk the codebase organically — don't follow rigid heuristics; note where you experience friction:

  • Where does understanding one concept require bouncing between many small files? That comprehension cost is the friction itself.
  • Where are modules shallow — interface nearly as complex as the implementation?
  • Where have pure functions been extracted just for testability, while the real bugs hide in how they're called (no locality)?
  • Where do tightly-coupled modules leak across their seams?
  • Which parts are untestable through their current interface — no seam to test at?

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 94 tokens per session scan A e9546134f068

Subscribe to this mod's changes

architecture is a skill published in the GitHub repository AbdurRafay2004/handoff (4 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,316 once invoked, about $0.0005 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 skills, from other repositories

focus

Declare a focus contract for the current task to keep context lean — scopes which files/dirs are in play, bans out-of-scope exploration, and routes broad searches to subagents. Use when starting a task, when the user says "focus on X", or when the session is drifting across unrelated parts of the codebase.

yanfeid/claude-amber · 66 tokens

checkpoint

Write the current working state (task, decisions, files touched, open problems, next steps) to .amber/STATE.md so it survives compaction and session restarts. Use when the user asks to checkpoint/save state, before risky long operations, when context feels heavy, or before ending a work session.

yanfeid/claude-amber · 62 tokens

diet

Audit what is eating the context window in this project (CLAUDE.md size, MCP servers, rules that should be skills) and produce a concrete slimming plan with estimated token savings. Use when the user complains about context filling up fast, frequent compaction, or asks to optimize/reduce context usage.

yanfeid/claude-amber · 61 tokens

resume

Reload saved working state from .amber/ (STATE.md, FOCUS.md, checkpoint.md) and continue the previous task. Use when the user says resume/continue where we left off, or at the start of a session in a project that has an .amber directory.

yanfeid/claude-amber · 55 tokens

building

Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.

romiluz13/cc10x · 53 tokens

memory-and-handoff

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.

romiluz13/cc10x · 70 tokens