Every claim in this book that rests on an external source is tagged with a <Citation> that resolves to an entry in this archive. The archive itself lives in version-controlled YAML; this page is the human-readable view. Ch 15’s source-tiering methodology is implemented concretely here — every source carries a tier from T1-official to T4-conjecture, and the audit cadence for each chapter is shaped by the tier mix of its cited sources.

How the archive works

The book ships a structured source manifest at sources/manifest.yaml. Each entry has a stable slug, a URL, a title, an author, a publish date, a capture date, a trust tier, and (optionally) a Perma.cc archival link and a hash of the locally-captured content.

Citations in chapter MDX reference the slug: <Citation src="gwern-sidenote" /> resolves at build time to the metadata below. The <Citation> component renders the trust tier as a badge so readers can calibrate their confidence at the point of use, and exposes the archival link when present.

The full captured HTML + PDF + screenshot of each source is held in the repo’s gitignored sources/cache/<hash>/ directory — used for drift detection (re-fetch periodically, compare hashes, flag significant changes) but never published. The defensive posture this creates (reader sees metadata and archival link, full cached content stays private) keeps the legal surface small while preserving the author’s ability to verify integrity.

The archive

The listing below is rendered live from sources/manifest.yaml at build time by the <SourceArchive /> component. Entries are grouped by tier in descending authority (T1 → T4); within a tier, newest publish dates come first. Empty tiers render an honest placeholder — the archive is intentionally sparse in the early book, and visible gaps are part of the pedagogy.

T1 · Official 26 entries

Vendor-official documentation or release notes. Highest trust for factual claims about the vendor’s own tool.

  1. Work with sessions
    original id: agent-sdk-sessions
  2. Subagents in the SDK
    original id: agent-sdk-subagents
  3. CLI reference
    original id: claude-code-cli-reference
  4. Commands
    original id: claude-code-commands
  5. Run Claude Code programmatically
    original id: claude-code-headless
  6. Hooks reference
    original id: claude-code-hooks
  7. Connect Claude Code to tools via MCP
    original id: claude-code-mcp
  8. How Claude remembers your project
    original id: claude-code-memory
  9. Choose a permission mode
    original id: claude-code-permission-modes
  10. Claude Code Settings
    original id: claude-code-settings
  11. Extend Claude with skills
    original id: claude-code-skills
  12. Codex CLI — Custom instructions with AGENTS.md
    original id: codex-cli-agents-md
  13. Codex CLI — Authentication
    original id: codex-cli-auth
  14. Codex CLI — Advanced configuration
    original id: codex-cli-config-advanced
  15. Codex CLI — Configuration reference
    original id: codex-cli-config-reference
  16. Codex CLI — Non-interactive mode
    original id: codex-cli-noninteractive
  17. OpenAI Codex CLI — lightweight coding agent for the terminal (repository)
    original id: codex-cli-repo
  18. Codex CLI — Agent approvals & security (sandbox)
    original id: codex-cli-sandbox
  19. Gemini CLI — Authentication
    original id: gemini-cli-authentication
  20. Gemini CLI — Commands reference
    original id: gemini-cli-commands-reference
  21. Gemini CLI — Configuration reference
    original id: gemini-cli-configuration
  22. Gemini CLI — Custom commands (TOML)
    original id: gemini-cli-custom-commands
  23. Gemini CLI — GEMINI.md context files
    original id: gemini-cli-gemini-md
  24. Gemini CLI — MCP servers
    original id: gemini-cli-mcp-server
  25. Gemini CLI — open-source terminal agent (README)
    original id: gemini-cli-readme
  26. Gemini CLI GitHub Action (google-github-actions/run-gemini-cli)
    original id: gemini-cli-run-action

T2 · Release notes no entries yet

Release blog posts, changelogs, conference talks. Trustworthy for intent and availability claims.

No sources at this tier yet.

T3 · Practitioner 2 entries

Respected community writing with a durable argument the author has defended over time.

  1. Sidenotes In Web Design
    original id: gwern-sidenote
  2. Tufte CSS
    original id: tufte-css

T4 · Conjecture no entries yet

Blog posts, tweets, or unverified claims. Pointers to investigate, not authorities.

No sources at this tier yet.

What’s coming

The archive is intentionally sparse at this point in the book’s development. Stage 3 of the roadmap expands it substantially:

Audit expectations

Per Ch 15’s methodology, each entry in the archive carries an implicit re-verification cadence based on its tier:

The archive’s integrity is the book’s integrity. A source whose content has shifted beneath a citation silently demotes the chapter that cited it to an unknown state. The drift-detection workflow above is the machinery that keeps the gap small; the human audit cadence is the safety net when the machinery misses something.

Quick reference