Skip to main content
reopt Handbook
reopt Handbook
Agentic Documentation

Paradigm Shift

Why Documentation Must ChangeAI-readable Design PrinciplesAI-assisted Writing Process

Practice by Document Type

Project Rule DocumentsFrom Docs to Skills, Plugins, and MCPAgent Documentation SecurityAPI Docs and SpecsREADME and OnboardingArchitecture Decision RecordsRunbooks and OperationsUser Guides and TutorialsKnowledge Bases and Internal Wikis

Operations

Maintenance StrategyTeam Documentation Culture

Appendix

TemplatesVerification ReportUpdates
Handbook›에이전틱 시대의 문서화 혁신›Verification Report
한국어English

Verification Report

Source, link, consistency, and build verification for the Agentic Documentation handbook.

Verification Date

Verified against the main external source set and local handbook checks on May 24, 2026.

Method

  • Reviewed official or primary source documents first.
  • Rechecked Codex, Claude Code, MCP, OpenAPI, llms.txt, and LLM security terminology.
  • Avoided presenting llms.txt as a guaranteed standard for crawler or search behavior.
  • Updated meta.json, contents, registry summary, and appendices together.
  • Ran local registry, typecheck, and build verification.

Source Baseline

TopicSourceUsed for
Codex AGENTS.mdOpenAI Codex: Custom instructions with AGENTS.mddiscovery order, overrides, size cap
Codex SkillsOpenAI Codex: Skillsskill structure and progressive disclosure
Codex PluginsOpenAI Codex: Build pluginsplugin manifest, MCP, hooks
Claude memoryClaude Code: How Claude remembers your projectCLAUDE.md, imports, local memory
Claude SkillsClaude Code: Skillsskill loading and support files
MCP conceptsModel Context Protocol: Understanding MCP serversTools, Resources, Prompts
MCP schemaModel Context Protocol Schema ReferenceTool annotations and schemas
MCP securityMCP Security Best Practicesconsent, scope minimization
OpenAPIOpenAPI Specification v3.2.0current spec baseline
OpenAPI 3.2OpenAPI Initiative: Announcing OpenAPI v3.2streaming, query, tags, OAuth metadata
LLM securityOWASP Top 10 for LLM Applicationsprompt injection, supply chain, excessive agency
AGENTS.mdAGENTS.mdshared agent instruction file concept
llms.txtThe /llms.txt fileMarkdown index proposal

Local Verification

CommandResult
pnpm --filter handbook run check:books-registrypassed
pnpm --filter handbook run typecheckpassed
pnpm --filter handbook run buildpassed, 1044 static pages generated

Remaining Limits

Fast-moving Surface

Codex, Claude Code, OpenAPI, MCP, and llms.txt continue to evolve. Recheck tool behavior and tooling support when there are major releases.

Related docs

Updates

Change log for the Agentic Documentation handbook.

API Docs and Specs

Connect OpenAPI 3.2, tool schemas, MCP Resources, and contract tests.

Terminal CLI Commands and Options

Codex Command Master · All 27 official Codex CLI command entries, global and command-specific option tables, and release additions

Ch7. Tools, Approval, Connections

Enterprise Eve Agent Development · Design Eve authored tools, human approval, MCP/OpenAPI connections, and OAuth boundaries as enterprise security surfaces.

Verification Report

Harness Engineering · Link, consistency, source, and static validation report for the Harness Engineering handbook.

Templates

Templates for AGENTS.md, CLAUDE.md, Skills, Plugins, MCP, llms.txt, runbooks, and KB docs.

Updates

Change log for the Agentic Documentation handbook.

On this page

MethodSource BaselineLocal VerificationRemaining Limits