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.

Topic	Source	Used for
Codex `AGENTS.md`	OpenAI Codex: Custom instructions with AGENTS.md	discovery order, overrides, size cap
Codex Skills	OpenAI Codex: Skills	skill structure and progressive disclosure
Codex Plugins	OpenAI Codex: Build plugins	plugin manifest, MCP, hooks
Claude memory	Claude Code: How Claude remembers your project	`CLAUDE.md`, imports, local memory
Claude Skills	Claude Code: Skills	skill loading and support files
MCP concepts	Model Context Protocol: Understanding MCP servers	Tools, Resources, Prompts
MCP schema	Model Context Protocol Schema Reference	Tool annotations and schemas
MCP security	MCP Security Best Practices	consent, scope minimization
OpenAPI	OpenAPI Specification v3.2.0	current spec baseline
OpenAPI 3.2	OpenAPI Initiative: Announcing OpenAPI v3.2	streaming, `query`, tags, OAuth metadata
LLM security	OWASP Top 10 for LLM Applications	prompt injection, supply chain, excessive agency
AGENTS.md	AGENTS.md	shared agent instruction file concept
llms.txt	The /llms.txt file	Markdown index proposal

Command	Result
`pnpm --filter handbook run check:books-registry`	passed
`pnpm --filter handbook run typecheck`	passed
`pnpm --filter handbook run build`	passed, 1044 static pages generated

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.

Verification Date

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

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.

Topic	Source	Used for
Codex `AGENTS.md`	OpenAI Codex: Custom instructions with AGENTS.md	discovery order, overrides, size cap
Codex Skills	OpenAI Codex: Skills	skill structure and progressive disclosure
Codex Plugins	OpenAI Codex: Build plugins	plugin manifest, MCP, hooks
Claude memory	Claude Code: How Claude remembers your project	`CLAUDE.md`, imports, local memory
Claude Skills	Claude Code: Skills	skill loading and support files
MCP concepts	Model Context Protocol: Understanding MCP servers	Tools, Resources, Prompts
MCP schema	Model Context Protocol Schema Reference	Tool annotations and schemas
MCP security	MCP Security Best Practices	consent, scope minimization
OpenAPI	OpenAPI Specification v3.2.0	current spec baseline
OpenAPI 3.2	OpenAPI Initiative: Announcing OpenAPI v3.2	streaming, `query`, tags, OAuth metadata
LLM security	OWASP Top 10 for LLM Applications	prompt injection, supply chain, excessive agency
AGENTS.md	AGENTS.md	shared agent instruction file concept
llms.txt	The /llms.txt file	Markdown index proposal

Command	Result
`pnpm --filter handbook run check:books-registry`	passed
`pnpm --filter handbook run typecheck`	passed
`pnpm --filter handbook run build`	passed, 1044 static pages generated

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.