ai-first-engineering

ai-first-engineering is a skill for Claude Code from shennawardana23/skillme. It costs 98 tokens per session (1,327 once invoked), scanned A, original, Apache-2.0.

Guidance for organizing an engineering team where AI agents write much of the code. It explains how planning, architecture, testing, code review, and hiring need to account for agent-written changes.

In plain words
What is it for?
Use it to design team workflows, architecture standards, review policies, testing expectations, and hiring or evaluation criteria for AI-assisted development.
Why use it?
AI can produce code quickly while still repeating the same misunderstanding, so teams need checks that expose behavioral errors and unclear plans.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skillme plugin — 137 skills, 2 commands shipped together

Good fit Use it to design team workflows, architecture standards, review policies, testing expectations, and hiring or evaluation criteria for AI-assisted development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shennawardana23/skillme/ai-first-engineering
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 shennawardana23/skillme --skill ai-first-engineering
Clone the repo
git clone --depth 1 https://github.com/shennawardana23/skillme

Made for: Claude Code.

Or install skillme, the plugin that ships this one along with the rest of its 137 skills, 2 commands.

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 ai-first-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/shennawardana23/skillme/ai-first-engineering/github.svg)](https://agentmods.dev/skills/shennawardana23/skillme/ai-first-engineering)
Your own site
<a href="https://agentmods.dev/skills/shennawardana23/skillme/ai-first-engineering"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/ai-first-engineering/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.

agentmods 80×15 button for ai-first-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/shennawardana23/skillme/ai-first-engineering"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/ai-first-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,327 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.01327
Opus 5 $0.00049 $0.00664
Sonnet 5 $0.00020 $0.00265
Haiku 4.5 $0.00010 $0.00133

Measured 12d ago against content hash 76a8136b2596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-first-engineering 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 12d 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/ai-first-engineering/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-First Engineering

The organizational operating model for a team where AI agents write a large share of the code: what changes about architecture, review, testing policy, and hiring when the median contributor to a diff is an agent directed by an engineer. This is a process/org-design skill — for how to run one task through an agent, see agentic-engineering.

What actually shifts

  1. Planning quality outweighs typing speed. When implementation is cheap, the bottleneck moves to whether the plan was correct — a precisely wrong plan gets implemented precisely and wrongly, fast.
  2. Eval coverage outweighs anecdotal confidence. "I tried it and it worked" doesn't scale when the person who tried it and the system that wrote it share the same blind spots (see ai-regression-testing).
  3. Review focus shifts from syntax to system behavior. Syntax and style are cheap for a model to get right; behavioral correctness under edge cases and load is not — review effort should follow the risk, not old habits about what code review used to catch.

Architecture that agents can work in safely

Prefer architectures with properties a model can reason about locally, without holding the whole system in context:

  • Explicit boundaries — a service or package's contract is written down, not inferred from reading five other files.
  • Stable, typed contracts — function signatures and API shapes that don't vary based on hidden runtime state.
  • Deterministic tests — a test that's flaky independent of the code under test teaches an agent (and a human) the wrong lesson about whether its change broke something.

Avoid implicit behavior spread across unwritten conventions ("we always do X in this codebase, it's just not documented anywhere") — a human engineer picks this up by osmosis over months; an agent starting a fresh session has no such history, and will violate the convention with full confidence.

Code review policy for AI-first teams

Read the full file on GitHub · 127 lines

Files

What ships with it

1 file 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.

  1. 12d ago First seen · 127 lines · 98 tokens per session scan A 76a8136b2596

Subscribe to this mod's changes

ai-first-engineering is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,327 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.