software-engineering-library

software-engineering-library is a skill for Claude Code, Codex from rjmurillo/ai-agents. It costs 201 tokens per session (1,001 once invoked), scanned A, original, MIT.

A reference guide for software design and code-risk questions, including architecture, module boundaries, domain modeling, refactoring, and older code. It points the agent to relevant book-based guidance when needed.

In plain words
What is it for?
Use it during architecture reviews, refactoring, legacy-code work, API and queue design, transaction decisions, or changes to module interfaces.
Why use it?
It gives the agent deeper explanations for design decisions instead of relying only on short, general advice. This helps when a change affects how parts of a system are organized or connected.

Skill for Claude CodeCodex

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 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/rjmurillo/ai-agents/software-engineering-library
Any agent
npx skills add rjmurillo/ai-agents --skill software-engineering-library
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code, Codex.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 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 software-engineering-library

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjmurillo/ai-agents/software-engineering-library.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/software-engineering-library)
Your own site
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/software-engineering-library"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/software-engineering-library.svg" alt="Measured on agentmods" height="20"></a>
Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,001 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 $0.00201 $0.01001
Opus 5 $0.00101 $0.00500
Sonnet 5 $0.00040 $0.00200
Haiku 4.5 $0.00020 $0.00100

Measured yesterday against content hash f2a91304df5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

software-engineering-library 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.

.claude/skills/software-engineering-library/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Engineering Library

This skill routes software engineering design work to deeper book-derived references without loading them on every turn.

For the everyday default, none loads on every turn and code-quality, pragmatic-programmer and unified-software-engineering load on code files; open a reference here only when the task needs that specific book's depth (start with one, add a second only when it changes a decision).

Triggers

  • architecture review
  • domain modeling bounded context
  • refactoring code smells legacy code low test coverage old file characterization tests
  • external API calls queues retries timeouts circuit breaker bulkhead
  • transactions event ordering data consistency schema evolution module interface shape

When Each Reference Applies

  • Use references/clean-architecture.md when dependency direction, layer ownership, or boundary placement drives the decision.
  • Use references/philosophy-of-software-design.md when module depth, interface shape, or complexity hiding drives the decision.
  • Use references/domain-driven-design.md when the work models a domain, splits bounded contexts, or translates across contexts.
  • Use references/enterprise-patterns.md when persistence, repositories, unit-of-work, transactions, or application service orchestration are central.
  • Use references/refactoring.md when changing internal structure, addressing code smells, or preserving behavior while improving shape.
  • Use references/working-with-legacy-code.md when the code is hard to test, poorly covered, or needs seams and characterization tests before change.
  • Use references/data-intensive-applications.md when state, storage, schema evolution, consistency, ordering, or delivery semantics are central.
  • Use references/release-it.md when production resilience, timeouts, circuit breakers, bulkheads, retries, and operational failure modes are central.

Task To Reference Router

Task Reference
Architecture / layer boundaries references/clean-architecture.md, references/philosophy-of-software-design.md
Domain modeling / bounded contexts references/domain-driven-design.md
Persistence / repository / unit-of-work references/enterprise-patterns.md
Refactoring / code smells references/refactoring.md
Legacy code / seams / characterization tests references/working-with-legacy-code.md
Data systems / consistency / schema evolution references/data-intensive-applications.md
Production resilience / timeouts / bulkheads references/release-it.md

Read the full file on GitHub · 73 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 · 73 lines · 201 tokens per session scan A f2a91304df5a

Subscribe to this mod's changes

software-engineering-library is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 201 tokens to every session and 1,001 once invoked, about $0.0010 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.