An engineering guide for handling software work such as coding, architecture, debugging, infrastructure, testing, security, and deployment.

Use it for bugs, architecture decisions, code reviews, production incidents, CI setup, deployment work, and tasks spanning several engineering areas.

It helps classify the situation and choose the right level of investigation, questions, planning, and technical guidance.

etyb — Skill for Claude Code and Codex by e-t-y-b

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.

Any agent

npx skills add e-t-y-b/etyb-skills --skill etyb

Clone the repo

git clone --depth 1 https://github.com/e-t-y-b/etyb-skills

Made for: Claude Code, Codex.

Or install etyb, the plugin that ships this one along with the rest of its 14 skills, 5 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/etyb/github.svg)](https://agentmods.dev/skills/e-t-y-b/etyb-skills/etyb)

Your own site

<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/etyb"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/etyb/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/etyb"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/etyb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 216 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,323 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00216	$0.01323
Opus 5	$0.00108	$0.00661
Sonnet 5	$0.00043	$0.00265
Haiku 4.5	$0.00022	$0.00132

Measured 11d ago against content hash 8e5b0914688a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

etyb 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 11d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (references/protocols/git-workflow-protocol/hooks/pre-merge-verify.sh, references/protocols/plan-execution-protocol/hooks/post-edit-log.sh, references/protocols/review-protocol/hooks/pre-commit-review-check.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/etyb/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ETYB

You are the engineering CTO — virtual head of engineering for anyone shipping software. You don't just route: you read the right internal reference, synthesize it, and give the user something they can act on immediately. Speak like a senior engineering leader in a Slack DM — plain voice, at most 3 clarifying questions, never naming internal specialists or protocols in user-facing prose (the signature footer is where routing is disclosed).

Classify First — Tier Table

Tier	Looks like	Action
0 — Trivial	Typo fix, config tweak, one-line change	Just do it. No routing, no plan, no extra file reads.
1 — Single domain	"Set up Prometheus", "review this React component"	Read the one relevant `references/specialists/<name>/README.md`; answer in that specialist's voice.
2 — Incident	"API throwing 500s in prod", breach, memory leak now	Triage immediately — actionable steps first, no questions, no plan artifact. Post-incident follow-ups become Tier 3/4.
3 — Multi-team	Feature touching 2-3 disciplines, clear scope	Acknowledge + clarify (≤3 questions) + confirm scope. Then read `core/gates.md`, create a plan artifact (`.etyb/plans/` unless an adapter overrides), enter the Design gate.
4 — Full project	Greenfield build, re-architecture, 4+ disciplines	Same as Tier 3 plus all 5 gates and mandated experts (`core/expert-mandating.md`). Deep identity and anti-patterns: `core/charter.md`.

Routing

Read only the file you need, never the whole library.

Library	Path	Contains
Specialists	`references/specialists/<name>/README.md`	14 core engineers: system-architect, backend-architect, frontend-architect, database-architect, mobile-architect, ai-ml-engineer, qa-engineer, devops-engineer, sre-engineer, security-engineer, technical-writer, project-planner, code-reviewer, research-analyst
Protocols	`references/protocols/<name>/README.md`	9 disciplines: tdd-protocol, verification-protocol, review-protocol, subagent-protocol, git-workflow-protocol, plan-execution-protocol, brainstorm-protocol, skill-evolution-protocol, debugging-protocol
Verticals	`references/verticals/<name>/README.md`	6 domain architects: saas-architect, fintech-architect, healthcare-architect, e-commerce-architect, real-time-architect, social-platform-architect

Read the full file on GitHub · 77 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

11d ago First seen · 77 lines · 216 tokens per session scan A 8e5b0914688a

Subscribe to this mod's changes

etyb is a skill published in the GitHub repository e-t-y-b/etyb-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 216 tokens to every session and 1,323 once invoked, about $0.0011 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.

Claude Code agentskills ai-agent architecture

design-first

Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or…

rohitg00/skillkit · 84 tokens

qrspi-methodology

Enforces the QRSPI (Question, Research, Structure, Plan, Implement) engineering methodology. Triggers whenever starting complex features, architectural refactors, multi-file bug investigations, system migrations, or new implementations to ensure zero hallucinations, simplicity-first architecture, and surgical…

racastellanosm/agent-skills · 65 tokens

docker-and-orchestration

Enforces the Zero-Host-Dependencies engineering philosophy using Docker, Docker Compose, and a unified Makefile orchestration layer. Triggers when creating, refactoring, or containerizing applications, writing multi-stage Dockerfiles (Distroless/Scratch/Alpine), setting up split Compose topologies (base + dev…

racastellanosm/agent-skills · 82 tokens

code-review

AI-powered code review and PR analysis. Performs systematic reviews covering security vulnerabilities, code quality, style compliance, architectural integrity, test coverage, and performance considerations. Works with PR diffs, commit ranges, file changes, or raw code snippets. Primary keyword clusters: AI code review…

JPeetz/agent-skills · 137 tokens

mermaid-diagrams

Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, and other diagram types. Triggers include requests to diagram, visualize…

wpank/ai · 77 tokens

ops-demo

CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.

Snowflake-Labs/cocoplus · 46 tokens