Internal accuracy pass against v2.1.220 — no missing upstream features, but broken example code, disagreeing counts, and metadata drift.
Functional fixes: pre-commit.sh now exits 2 so it actually blocks; dependency-check.sh reads file_path from stdin JSON instead of $1; database-mcp.json uses ${DATABASE_URL}; broken fences repaired; three command templates had invalid skill names.
Factual corrections: /fork and /subtask unswapped and /subtask added; /fewer-permission-prompts; permissions.defaultMode; dontAsk/auto unreversed; 31 hook events verified name-by-name; subagent depth 3; skill precedence enterprise > project > personal; /output-style removed not deprecated; permissionDecision gained defer.
Follow-up review fixed defects the pass left behind: zh/vi headers claiming 31 events above 25-name lists, a surviving hardcoded DB credential in the MCP README examples, an unbalanced fence swallowing a metadata footer, and non-canonical tool names. All four translated CATALOG summary tables were recounted so their arithmetic holds.
Full detail in CHANGELOG.md under v2.1.220-r2.
Bumps tutorial coverage from the v2.1.217 baseline (2026-07-22 sync) to
v2.1.220 — three contiguous releases (v2.1.218–v2.1.220).
Critical fixes:
- Nested subagent spawning is on by default again at depth 3 (v2.1.219).
Five locations across 04-subagents, CATALOG, 10-cli and QUICK_REFERENCE
stated it was disabled by default — true for v2.1.217–v2.1.218 only.
CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=1 now disables rather than enables.
All five carry an identical three-era history note.
- Claude Opus 5 is the default Opus model (v2.1.219). 10-cli asserted
"Opus 4.8 remains the default"; Opus 5 was absent from every model table.
Added to both model tables, 19 Compatible Models footers, and ~20
effort-level enumerations.
Also fixed: fast-mode model list, auto-mode eligibility self-contradiction
in 09-advanced-features, stale CLAUDE_CODE_ENABLE_AUTO_MODE opt-in in
CATALOG, hook-event count disagreement (29/30 -> 31 across three files),
doc-generator skill name/directory mismatch, stale "May 2026" headings,
and the last three docs.anthropic.com links.
Added: DirectoryAdded hook, /deep-research explicit-invocation note,
/code-review background subagent, context:fork background default, agent
frontmatter hook workspace trust, dynamic workflow size guideline and
workflowSizeGuideline key, sandbox.network.strictAllowlist, MCP error
surfacing, stream-json nested subagent forwarding, frontmatter boolean
values, agent name ':' rejection, auto/plan-mode classifier changes, and
Opus 5 safety-classifier fallback.
Renamed the deep-research skill example to topic-research to stop it
shadowing the built-in; mirrored to vi/ja/uk. doc-generator rename
mirrored to ja/zh/uk.
Bumps tutorial coverage from the v2.1.212 baseline (2026-07-18 sync) to
v2.1.217 (v2.1.213 was skipped upstream), plus a repo-internal accuracy
audit.
Fixed:
- Nested-subagent-spawning claim reversed (v2.1.217): 04-subagents/README.md
and CATALOG.md stated nesting up to 5 levels as current behavior; as of
v2.1.217 it's off by default, opt in via CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH
- Stale --enable-auto-mode flag (removed in v2.1.111) replaced with
--permission-mode auto across 10-cli/README.md and QUICK_REFERENCE.md
- Import-depth contradiction in 02-memory/README.md: two remaining "5 levels"
instances corrected to "4 hops", matching the rest of the file
- Sonnet 5 added to claude_concepts_guide.md's models/reasoning-effort table
- config-examples.json's fabricated settings schema (fake "unrestricted"/
"confirm" modes, undocumented keys) rewritten to real settings.json keys
- brand-voice skill (name/user-invocable) aligned to its README worked example
- CLAUDE.md length guidance unified across 03-skills/claude-md/SKILL.md and
02-memory/README.md
Added:
- New subagent caps (v2.1.217): CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS
- --max-budget-usd now also halts running background subagents (v2.1.217)
- Hook if: glob scope narrowed to <cwd>/dir (v2.1.214), documented in
06-hooks/README.md along with SessionStart's new "fork" source
- sandbox.filesystem.disabled setting (v2.1.216)
- /rewind symlink/hard-link protection (v2.1.216)
- Auto-memory modified timestamp (v2.1.214) and non-blocking /memory editor
(v2.1.216)
- CLI/settings batch (v2.1.214-217): emojiCompletionEnabled,
FORCE_HYPERLINK=0, CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH, --settings 2 MiB
cap, permission hardening notes, /context and /compact notes
- /verify and /code-review explicit-invocation-only note (v2.1.215)
Mirrored applicable P0/P1 fixes into vi/ja/zh/uk translations where the
same claim existed.
* docs: sync to Claude Code v2.1.212
Bumps tutorial coverage from the v2.1.206 baseline (2026-07-11 sync) to
v2.1.212, plus a repo-internal accuracy audit that surfaced defects
independent of the version delta.
Fixed:
- Dead `#` memory-shortcut removed from 02-memory/README.md (two places
documented a discontinued quick-memory-add pattern as working, directly
contradicting the file's own commands table)
- Auto mode opt-in -> opt-out on Bedrock/Vertex/Foundry (v2.1.207)
- `auto` permission mode mislabeled "Research Preview" across
09-advanced-features/README.md, CATALOG.md, README.md, and the vi/ja/zh/uk
translations (auto mode is GA, gated only by plan/model/provider)
- `/fork` / `/branch` history corrected: they were a single aliased command
only from v2.1.77 to v2.1.161, not "renamed" as previously stated
- `effort` frontmatter enum in 04-subagents/README.md completed with `xhigh`
- Bundled-skills count reconciled in CATALOG.md (9 -> 10)
- INDEX.md Skills section count and Feature Coverage Matrix Total column
fully recomputed and reconciled (Skills: 22, Plugins: 39)
- Stale 2.1.160 footer cluster (5 files) bumped to 2.1.212
- QUICK_REFERENCE.md fully resynced (was 52 versions behind)
- 02-memory/README.md's Memory Hierarchy section rewritten: replaced a
fabricated 8-tier strict-precedence model with the verified structure
(CLAUDE.md files are concatenated into context, not overridden; 4 real
location tiers; rules and auto memory are separate mechanisms)
- 02-memory/README.md's Memory Architecture diagram no longer conflates
claude.ai's 24h synthesis cycle with Claude Code's continuous auto memory
- Import recursion depth corrected (was documented as 5, actually 4 hops)
Added:
- Subagent output scanning (v2.1.210) documented in 04-subagents/README.md
- Session-wide spawn caps (v2.1.212): WebSearch and subagent limits
- MCP long-running-tool auto-backgrounding (v2.1.212) in 05-mcp/README.md
- `claude auto-mode reset` and `/resume` picker (v2.1.212)
- Screen reader mode (v2.1.208): --ax-screen-reader / CLAUDE_AX_SCREEN_READER
- Task tool `mode` parameter deprecation note (v2.1.212)
Known gaps (deferred, not fixed this pass):
- 03-skills/blog-draft/ vs 03-skills/.claude/skills/blog-draft/: confirmed
the latter is gitignored local testing scratch, not a repo duplicate
* fix(INDEX): correct Skills row arithmetic and stale changelog notes
INDEX.md's Skills header/matrix shipped as 22 (5+9+8) despite the PR's
own CHANGELOG claiming it was fixed to 21 — three independent counts
(file-type breakdown, filesystem listing, changelog intent) agree on
21; the Docs column was off by one. Also removes two stale CHANGELOG
"Known gaps" entries this same PR already resolved (memory hierarchy
rewrite, blog-draft gitignore confirmation) and adds the missing
Fixed-section bullet documenting the memory hierarchy rewrite.
Bumps tutorial coverage from v2.1.138 → v2.1.143. Highlights:
- /goal and /scroll-speed slash commands (v2.1.139)
- claude agents Agent View (Research Preview) with 9 dispatch flags
- claude plugin details and marketplace context-cost projection
- Hook exec form (args), continueOnBlock on PostToolUse, terminalSequence
- Stop hook 8-block safety cap + override env var
- Fast Mode default flipped to Opus 4.7 (v2.1.142)
- PowerShell tool default-on for Bedrock/Vertex/Foundry on Windows
- API-key auth disables Remote Control, /schedule, claude.ai MCP, notifications
- worktree.bgIsolation setting
- CLAUDE_PROJECT_DIR for MCP stdio servers
- Subagent OTEL headers + case-insensitive subagent_type matching
- Root-level SKILL.md plugin pattern; Routines marketing name note
Also bumps stale "28 hook events" counts in CATALOG/README to 29 and
refreshes the metadata footer (Last Updated, Claude Code Version,
Sources) on every modified file.
Documents the v2.1.131 → v2.1.138 sync (PR #117) in the same format
as the v2.1.131 entry. Pattern caught during release-manager review;
the original sync PR did not include a CHANGELOG update.
Sync covers v2.1.128, v2.1.129, and v2.1.131 (May 2026). Highlights:
gateway /v1/models discovery is now opt-in (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY),
added --plugin-url flag, disableRemoteControl setting, /mcp tool-count display,
expanded skillOverrides values, /context viz no longer leaks into conversation,
Ctrl+R cross-project default. Also reconciles slash-command count to 60+ and
fixes the skill-count entry in CATALOG.
- Backfill CHANGELOG.md with v2.4.0 entry summarizing the
v2.1.112 → v2.1.119 sync work
- Refresh SECURITY.md footer (Last Updated April 27, 2026;
Next Review April 2027)
- Fix model ID in 09-advanced-features/config-examples.json:
claude-opus-4 → claude-opus-4-7 (3 occurrences) for
consistency with documented model IDs
- Remove RELEASE_NOTES.md stub that duplicated and contradicted
CHANGELOG.md
Sync all English tutorials with Claude Code v2.1.112 and the new Opus 4.7
model (claude-opus-4-7). Introduces the xhigh effort level (new default on
Opus 4.7), two new built-in slash commands (/ultrareview,
/less-permission-prompts), auto mode without --enable-auto-mode for Max
subscribers on Opus 4.7, PowerShell tool on Windows, Auto-match-terminal
theme, and plan files named after prompts. All 18 EN doc footers bumped to
Claude Code v2.1.112.
Version callouts in README.md, zh/README.md, and uk/README.md updated to
v2.1.112. Changelog entry prepended.
Repo version now tracks Claude Code version (2.3.0 → 2.1.112 is intentional
per new convention).
Luong NGUYEN