lfe-architect

lfe-architect is a skill for Claude Code, Codex from StChiotis/Library-First-Engineering. It costs 26 tokens per session (1,690 once invoked), scanned A, original, MIT.

An LFE workflow skill for acting as the Architect: the role that turns a requested change into a detailed implementation plan. It coordinates project review, requirements, work slices, and plan checks.

In plain words
What is it for?
Use it to investigate a change, write project plans in `.plans`, split work into approved pieces, and check whether a plan is ready to implement.
Why use it?
It creates a shared, reviewable plan before code is changed and enforces boundaries such as keeping core logic in the right modules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to investigate a change, write project plans in .plans, split work into approved pieces, and check whether a plan is ready to implement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stchiotis/library-first-engineering/lfe-architect
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 StChiotis/Library-First-Engineering --skill lfe-architect
Clone the repo
git clone --depth 1 https://github.com/StChiotis/Library-First-Engineering

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 lfe-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/stchiotis/library-first-engineering/lfe-architect"><img src="https://agentmods.dev/badge/skills/stchiotis/library-first-engineering/lfe-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,690 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 $0.00026 $0.01690
Opus 5.5 $0.00010 $0.00676
Sonnet 5.5 $0.00005 $0.00338
Haiku 4.5 $0.00003 $0.00169

Measured 1mo ago against content hash 5d5391bf2940, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lfe-architect 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 1mo 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.

.agents/skills/lfe-architect/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LFE Architect — The Thinker

Mission

Convert intent into a rigorous plan in .plans/active_plan.md. You are the gatekeeper of architectural integrity.

Sub-Pipeline (execute in this order)

  1. /lfe-grill-with-docs → writes .plans/01_grill_summary.md
  2. /lfe-to-prd → reads 01, writes .plans/02_prd.md
  3. /lfe-to-issues → reads 02, writes .plans/03_slices.md → 🛑 Human approves slices
  4. Draft active_plan.md for current slice (reads 03) → 🛑 Human approves plan
  5. /lfe-plan-critique → reads active_plan.md, runs a mechanical pre-pass + 5-lens review, writes .plans/plan_critique.md → 🛡 Auto-gate (PASS / WARN / BLOCK)

Hard Rules

  1. Zero Code Edits: edit only .docs/** and CONTEXT.md; leave src/** untouched.
  2. Logic Sovereignty: identify whether the change touches the Main Engine (the project's core-logic module).
  3. Complexity Gate: You must confirm if the user chose "Full Pipeline" or "Scout Mode" during boot.
  4. File-Based Handoffs: Each step reads the previous step's coordination file, not the conversation.

Workflow

  1. Design Tree: Visualize the impact. Identify every module that will be touched.
  2. The Grill Phase (Mandatory): Run /lfe-grill-with-docs first; propose a plan only once shared understanding is reached and 01_grill_summary.md is written.
  3. PRD Phase: Run /lfe-to-prd to synthesize the grill output into a structured PRD.
  4. Slicing Phase: Run /lfe-to-issues to break the PRD into vertical slices. Wait for human approval.
  5. Risk Assessment: Identify "High Risk" zones (core math, state management, security). Determine if automated tests are required.
  6. Active Plan: Draft .plans/active_plan.md for the current slice. Frontmatter follows the contract in COORDINATION_FILES.md:
---
phase: architect
step: 4_active_plan
status: complete
timestamp: <ISO-8601>
source: .plans/03_slices.md
slice: <slice number from 03_slices.md>
---

Read the full file on GitHub · 93 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. 1mo ago First seen · 93 lines · 26 tokens per session scan A 5d5391bf2940

Subscribe to this mod's changes

lfe-architect is a skill published in the GitHub repository StChiotis/Library-First-Engineering (46 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 1,690 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

ai-engineering-toolkit

Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

promptfoo-provider-setup

Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.

promptfoo/promptfoo · 66 tokens

avoid-ai-writing

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…

conorbronsdon/avoid-ai-writing · 97 tokens

prompt-master

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…

nidhinjs/prompt-master · 78 tokens

voice-preserving-rewriter

Use when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and protected material.

conorbronsdon/avoid-ai-writing · 46 tokens

flux2-lora-training

Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.

AnastasiyaW/codex-claude-code-config · 73 tokens