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/rootbr/rooted/architecting-codenpx skills add rootbr/rooted --skill architecting-codegit clone --depth 1 https://github.com/rootbr/rootedWhat 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 | $0.00167 | $0.02349 |
| Opus 5 | $0.00084 | $0.01175 |
| Sonnet 5 | $0.00033 | $0.00470 |
| Haiku 4.5 | $0.00017 | $0.00235 |
Grade A, and why
architecting-code 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecting Code
Evidence base: Robert C. Martin, Clean Architecture: A Craftsman's Guide to Software Structure and Design (Pearson, 2017). Chapter references cite Clean Architecture unless noted.
Load-bearing rule — architecture is measured by cost of change
Architecture is "the significant design decisions that shape a system, where significant is measured by cost of change" (Booch, via Henney, Foreword). Optimise the kinds of changes the system actually experiences to be cheap, not rare — and size the architecture to the problem, not to a textbook.
The Dependency Rule
- Source-code dependencies always point toward higher-level policy; details implement interfaces owned by the policy layer — the DIP mechanism that makes the rule enforceable (PART III SOLID summary; Appendix A ROSE)
- When crossing a boundary, invert the dependency so the caller holds an interface the detail implements (Appendix A, Union Accounting)
- High-level policy compiles with zero knowledge of UI, database, or framework types — only of the abstractions it owns (Ch 17; Appendix A 4-Tel Vectorization)
SOLID at the module level
- SRP — every module has exactly one reason to change, defined by one actor/stakeholder (Ch 7; PART III summary)
- OCP — add new behaviour by adding new code, not by editing existing, already-tested code (Ch 8; PART III summary)
- LSP — a subtype's contract must allow substitution anywhere the supertype is used, including in tests (Ch 9)
- ISP — never force a module to depend on interface members it doesn't use; unused methods still pin recompile/redeploy (Ch 10)
- DIP — high-level policy never imports concretions; details implement policy-owned interfaces; factories sit at the boundary (Ch 11)
Component cohesion (what belongs together)
- REP — Reuse/Release Equivalence — the granule of reuse is the granule of release; unreleased code is not reusable (Ch 13)
- CCP — Common Closure — classes that change together belong in the same component (component-level SRP) (Ch 13)
- CRP — Common Reuse — classes that are used together belong in the same component; never drag unrelated classes along (component-level ISP) (Ch 13)
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.
- 2d ago First seen · 115 lines · 167 tokens per session scan A 8c623dd01765
architecting-code is a skill published in the GitHub repository rootbr/rooted (21 stars, last pushed 26d ago), licensed Apache-2.0. It adds 167 tokens to every session and 2,349 once invoked, about $0.0008 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…