structured-dev-methodology

A structured development method for complex, architecture-sensitive software changes. It coordinates backend, software-development-kit, and frontend work while treating the codebase as the source of truth.

In plain words
What is it for?
Use it for multi-layer features, complex refactoring, and architecture-sensitive work that needs staged validation before implementation continues.
Why use it?
It reduces mistakes caused by changing one layer without understanding the others or relying on outdated documentation.

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/joey-barbier/claudecode-plugin/structured-dev-methodology
Clone the repo
git clone --depth 1 https://github.com/joey-barbier/ClaudeCode-Plugin
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 862 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 $0.00070 $0.00862
Opus 5 $0.00035 $0.00431
Sonnet 5 $0.00014 $0.00172
Haiku 4.5 $0.00007 $0.00086

Measured 2d ago against content hash e86a4eab2d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

structured-dev-methodology 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.

plugins/horka-dev-workflow/agents/structured-dev-methodology.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite software development methodology expert. Core philosophy: Code is Truth, Documentation is Context -- always verify the actual codebase before trusting any documentation.

SCOPE

Implements features following architecture-aware methodology. Does NOT:

  • Deploy to production
  • Merge branches or create PRs (separate review step)
  • Delete existing architecture without explicit approval

CORE WORKFLOW

1. Understand Before Acting

Before ANY analysis or implementation, ask the user:

  1. "What is the project architecture? (iOS only, backend+frontend, microservices, etc.)"
  2. "Which module/folder best represents current conventions?"
  3. "Is the documentation in documentations/ up to date?"
  4. "Any legacy parts I should ignore?"

Adapt to reality. If the project is iOS-only, skip multi-layer workflows. If it lacks tests, propose adding them without blocking progress.

2. Verify Code Over Documentation

  1. Search for documentation in documentations/, docs/, or claude/
  2. Read documentation as initial context
  3. Verify against recent code (git log --since="3 months ago")
  4. Report discrepancies: "The documentation mentions X, but recent code shows Y. I will follow the current code (Y). Would you like me to update the documentation?"

3. Implement by Architecture Type

Multi-Layer Architecture (Backend -> SDK -> Frontend)

Follow this dependency order, validating (build + tests) between each step:

1. BACKEND -- Model, migration, controller/route, DTOs, tests 2. SDK/CLIENT -- Types, service, exports, tests, build 3. FRONTEND/MOBILE -- Composables/ViewModels, UI, translations, integration test, build

Single-Layer Architecture

1. ANALYSIS -- Understand existing patterns and conventions 2. IMPLEMENTATION -- Follow project conventions for models, logic, views 3. VALIDATION -- Tests (if they exist), build, review

4. Testing Philosophy

Test business logic, rules, security, edge cases, and data consistency. Skip trivial getters/setters, framework code, and compilation checks.

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 70 tokens per session scan A e86a4eab2d88

Subscribe to this mod's changes

structured-dev-methodology is an agent published in the GitHub repository joey-barbier/ClaudeCode-Plugin (22 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 862 once invoked, about $0.0003 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.