ai-first-engineering

ai-first-engineering is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 19 tokens per session (544 once invoked), scanned A, original, Apache-2.0.

An engineering approach for building software that AI agents can plan, change, and test reliably. It emphasizes clear boundaries, typed data, repeatable tests, and checks for failure cases.

In plain words
What is it for?
Use it to plan features, design service and API boundaries, define data formats, write repeatable tests, and review refactors.
Why use it?
It reduces unclear requirements, flaky tests, and changes that are difficult for an agent to understand or verify.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan features, design service and API boundaries, define data formats, write repeatable tests, and review refactors.

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

Made for: Claude Code, Codex.

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/jxoesneon/ciel/ai-first-engineering/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/ai-first-engineering)
Your own site
<a href="https://agentmods.dev/skills/jxoesneon/ciel/ai-first-engineering"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/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/jxoesneon/ciel/ai-first-engineering"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ai-first-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 544 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 $0.00019 $0.00544
Opus 5 $0.00010 $0.00272
Sonnet 5 $0.00004 $0.00109
Haiku 4.5 $0.00002 $0.00054

Measured 8d ago against content hash adaba4dafe6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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 · 77 lines

What it actually says

CIEL ADAPTATION: AI-First Engineering

This skill provides CIEL's core philosophy for engineering in an AI-native environment. It prioritizes planning quality, deterministic verification, and agent-friendly architectures.

Integration Context

Adapted from ~/.agents/skills/ai-first-engineering/. This is CIEL's "Cultural Directive" for how it designs its own processes and reviews.

Core Mandates

1. Planning Over Typing

The orchestration skill must prioritize the "Research -> Strategy" phase. Implementation is a derivative of a well-defined plan.

2. Agent-Friendly Architecture

When proposing refactors or new features, prioritize:

  • Explicit Boundaries: Decoupled services and clear API contracts.
  • Typed Interfaces: Use TypeScript, Zod, or formal schemas for all data flow.
  • Deterministic Tests: No flaky tests; every failure must be reproducible.

3. Elevated Testing Standard

For all CIEL-orchestrated work:

  • Regression coverage is mandatory for touched domains.
  • Explicit assertions for edge cases and failure modes.
  • Integration checks for all interface boundaries.

Orchestration Logic

1. Architectural Review

The Council of Five must evaluate all major architectural proposals against the "Agent-Friendly" criteria.

2. Review Focus

CIEL's internal code review (via agentic-engineering) must focus on system behavior, security, and integrity, ignoring style issues covered by automation.

3. Hiring & Evolution

Use this skill to refine CIEL's own "Self-Improvement" strategies, focusing on the quality of its own generated plans and evals.


Original Documentation preserved at source.

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. 8d ago First seen · 77 lines · 19 tokens per session scan A adaba4dafe6a

Subscribe to this mod's changes

ai-first-engineering is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 544 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

review-tests

Reviews test quality and coverage. Use when checking that a diff has adequate tests, checking a new or edited test, or auditing the test suite of a codebase.

mrinalwadhwa/fluent · 36 tokens

testing-rate-limiting

Apply deterministic SlowAPI rate-limiter isolation for FastAPI transport tests, especially to avoid flaky HTTP 429 responses.

asap-protocol/asap-protocol · 29 tokens

fluent

Operate the fluent workflow to build software autonomously over extended periods. Interactive stages (brief, behaviors, approach, plan) run with the user. Autonomous execution loops writer → tester → parallel reviewers, then runs the Learner after a passing review round. Only a successful Learner run produces a ready…

mrinalwadhwa/fluent · 116 tokens

test-scaffold

Gera estrutura completa de testes automatizados (unitários, integração e edge cases) com base no código existente. Use para "escrever testes para este arquivo", "aumentar cobertura" ou "criar mocks".

rcelebrone/DotAgents · 49 tokens

e2e-runner

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

Kacper0199/Opencode-Ultrathinker · 59 tokens

tdd-workflow

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Kacper0199/Opencode-Ultrathinker · 43 tokens