docs-architect

docs-architect is a skill for Claude Code, Codex from JOndarza/loadout. It costs 120 tokens per session (6,105 once invoked), scanned B, original, MIT.

A documentation setup that keeps full human documentation alongside short, selectively loaded instructions for Claude Code, an AI coding tool.

In plain words
What is it for?
Use it to create or maintain project rules, architecture and stack documentation, path-specific guidance, and a clear structure for AI-assisted development.
Why use it?
It gives the AI only the project guidance needed for a task while keeping detailed reference material available to people.

Skill for Claude CodeCodex

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/jondarza/loadout/docs-architect
Any agent
npx skills add JOndarza/loadout --skill docs-architect
Clone the repo
git clone --depth 1 https://github.com/JOndarza/loadout

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 docs-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/jondarza/loadout/docs-architect.svg)](https://agentmods.dev/skills/jondarza/loadout/docs-architect)
Your own site
<a href="https://agentmods.dev/skills/jondarza/loadout/docs-architect"><img src="https://agentmods.dev/badge/skills/jondarza/loadout/docs-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00120 $0.06105
Opus 5 $0.00060 $0.03053
Sonnet 5 $0.00024 $0.01221
Haiku 4.5 $0.00012 $0.00611

Measured 3d ago against content hash dff7352ef176, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

docs-architect scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Always-loaded rules** — frontmatter-less `.claude/rules/*.md` files load at session start alongside `CLAUDE.md`. Use for universally-needed content (business, stack, conventions, core architecture).
.claude/skills/docs-architect/SKILL.md · 424 lines

How it starts

The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Architect — AI-Optimized Documentation (v2)

Build and maintain documentation that rides on Claude Code's native loading mechanisms. Cuts AI token consumption by 20–40% versus the v1 custom-summary pattern while preserving all information and giving humans a clean reference.

Core principle

Docs are a knowledge base. The AI receives only what is strictly necessary per task. v2 uses the official .claude/rules/ mechanism with two loading modes:

  • Always-loaded rules — frontmatter-less .claude/rules/*.md files load at session start alongside CLAUDE.md. Use for universally-needed content (business, stack, conventions, core architecture).
  • Path-scoped rules.claude/rules/*.md with paths: frontmatter auto-load only when Claude reads matching files. Zero startup token cost. Use for subsystem-specific rules (backend, frontend, api, database, testing).

Full human docs live in docs/*.md as the source of truth. .claude/rules/*.md are lean (≤40 lines, ≤12 bullets) distillations mirrored from the full docs.

Architecture

./CLAUDE.md                            # <100 lines — hard NOs + pointer to rules
./.claude/rules/                       # AI-facing rules (flat, no subfolders)
  ├── business-context.md              # always-loaded
  ├── coding-rules.md                  # always-loaded
  ├── tech-stack.md                    # always-loaded
  ├── architecture.md                  # always-loaded
  ├── backend.md                       # path-scoped: backend/**
  ├── frontend.md                      # path-scoped: frontend/**
  ├── api.md                           # path-scoped: **/Controllers/**, **/routes/**
  ├── database.md                      # path-scoped: **/Entities/**, **/migrations/**
  └── testing.md                       # path-scoped: **/*.test.*, **/tests/**
./.claude/agents/doc-explorer.md       # research subagent (isolated context)
./.claude/commands/                    # /docs-audit, /docs-sync, /docs-migrate
./docs/                                # full human-readable reference
  ├── README.md                        # governance + index
  ├── architecture.md                  # full architecture doc
  ├── coding-rules.md                  # full conventions
  ├── tech-stack.md                    # full package catalog
  ├── api-contracts.md                 # full endpoint catalog
  ├── database-schema.md               # full table catalog
  ├── deployment.md                    # full dev/prod reference
  ├── roadmap.md                       # product phases, KPIs, decisions
  ├── backlog.md                       # story registry
  ├── bugs.md                          # bug registry
  ├── ideas.md                         # raw ideas inbox
  ├── stories/ bugs/ plans/            # individual item files
  └── research/                        # deep reference docs

Read the full file on GitHub · 424 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. 3d ago First seen · 424 lines · 120 tokens per session scan B dff7352ef176

Subscribe to this mod's changes

docs-architect is a skill published in the GitHub repository JOndarza/loadout (2 stars, last pushed 4mo ago), licensed MIT. It adds 120 tokens to every session and 6,105 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

muapi-media-editing

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

SamurAIGPT/Generative-Media-Skills · 41 tokens

ctf-malware

Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…

ljagiello/ctf-skills · 101 tokens

research

Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.

Weizhena/Deep-Research-skills · 25 tokens

mcp-scripting

Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.

nicobailon/pi-mcp-adapter · 21 tokens