* docs: sync to Claude Code v2.1.156 and Claude Opus 4.8
Model bump Opus 4.7 -> Opus 4.8 and version sync v2.1.150 -> v2.1.156.
- Rewrite effort-ladder claims for Opus 4.8 (default `high`; `xhigh` on
4.8/4.7; `max` on 4.8/4.7/4.6 and Sonnet 4.6; Haiku has no effort).
- Replace soon-removed CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE with the
`/model claude-opus-4-6[1m]` + `/fast on` path; note Opus 4.8 fast mode.
- Bump lineup tables to Opus 4.8; fix Haiku 4.5 context (1M -> 200K).
- Sweep Compatible Models + version/date footers to 2.1.156 / May 29, 2026
across 23 English docs (incl. 2.1.138/2.1.145 stragglers).
- Re-document `/simplify` as a distinct cleanup-only command (v2.1.154).
- Add Dynamic Workflows + `/workflows`, MessageDisplay hook (count 29->30),
disallowed-tools frontmatter, `/reload-skills` + SessionStart outputs,
`/model` default-save inversion, lean system prompt, status-line
COLUMNS/LINES, and the ultracode `/effort` note.
* docs(cli): drop unverified fast-mode dollar pricing, keep verified rate/speed multipliers
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.
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.
Closes#99
- Replace shell-interpolated JSON build with the argv-based Python pattern
from session-end.sh, so notes containing quotes or backslashes don't
produce invalid JSON.
- Add mkdir/cp/chmod install block before the Configuration section so
the path in settings.json resolves to a real file.
* feat(hooks): add SessionEnd progress logger and local progress tracker
Adds a SessionEnd hook that prompts for modules studied at session end
and appends a record to ~/.claude-howto-progress.json — outside the repo
so progress survives git pull without being overwritten.
Also adds local-progress/index.html: a self-contained visual tracker
with checkboxes for all 10 modules, per-module notes, an overall progress
bar, and Export/Import to sync with a local JSON backup file.
Key patterns demonstrated:
- SessionEnd vs Stop (fires once on exit, not after every response)
- /dev/tty for interactive input in hooks (stdin carries the JSON payload)
- $CLAUDE_PROJECT_DIR for portable paths (never hardcode /Users/...)
- Guard clause to prevent global hook running in unrelated projects
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
* fix(hooks): address PR review — bash 3.2 compat, JSON escaping, textarea XSS
- Replace pipeline+while with IFS for-loop (bash 3.2 compatible)
- Pass NOTES as Python arg to avoid broken JSON on quotes/backslashes
- Set textarea.value instead of innerHTML to prevent XSS from imported JSON
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
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).
* docs: sync to Claude Code v2.1.110 with TUI, push notifications, session recap, and new commands
- 01-slash-commands: add /tui, /focus, /recap, /undo, /proactive to command table and recent changes
- 07-plugins: document monitors manifest key for background monitor support (v2.1.105)
- 09-advanced-features: add TUI mode, push notifications, session recap, ENABLE_PROMPT_CACHING_1H
- 10-cli: add --exclude-dynamic-system-prompt-sections flag and CLAUDE_CODE_PERFORCE_MODE env var
- CATALOG.md: update command counts (55+→60+, 63+→68+), add 5 new command rows
- All 12 files: bump footer to April 16, 2026 / Claude Code Version 2.1.110
* fix(catalog): correct version tags for /proactive, /recap, /undo commands
/proactive was added in v2.1.105, /recap and /undo in v2.1.108 — not v2.1.110.
Only /tui and /focus were introduced in v2.1.110.
The pre-tool-check.sh example had three bugs rooted in the same
misunderstanding of the Claude Code PreToolUse hook protocol
(stdin/stdout/stderr + exit code contract):
1. Substring matching on `rm -rf /`
The pattern was unanchored, so grep treated it as a substring and
falsely blocked any command containing `rm -rf /` — including benign
calls like `rm -rf /tmp/build` or `rm -rf /var/cache/foo`. Fixed by
anchoring the slash to a whitespace-or-end-of-line boundary.
2. WARN tier was dead code
The warning layer printed to stderr and then `exit 0`. Claude Code
silently discards stderr on exit 0, so the warnings were never seen
by Claude, the user, or any log. Fixed by adding an audit log file
at `$CLAUDE_PROJECT_DIR/.claude/hooks/audit.log` that records every
invocation with its decision (BLOCK/WARN/ALLOW). The audit log is
now the reliable observability mechanism for the WARN tier.
3. BLOCK reasons printed to stdout instead of stderr
On `exit 2`, Claude Code reads stderr to surface the block reason
to Claude. The echoes before `exit 2` defaulted to stdout, so
Claude Code reported `"No stderr output"` and Claude had to read
the hook source file to infer why a command was blocked. Fixed by
explicitly redirecting the block-reason echoes to stderr with `>&2`.
Also escaped the regex metacharacters in the fork-bomb pattern
`:(){:|:&};:` so it matches literally under `grep -E`, and updated the
header docstring to document the stdout/stderr/exit-code convention so
future readers don't make the same mistakes.
Verified with 6 smoke tests covering: benign command (ALLOW), warn-tier
relative path, substring edge case (`rm -rf /tmp/...` no longer falsely
blocked), exact root match (`rm -rf /`, `rm -rf / ; echo` still blocked),
fork-bomb literal, and `git push --force` (WARN only). stdout is empty
in all cases; all reasons correctly routed to stderr or the audit log.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: sync to Claude Code v2.1.101 with new feature coverage
Bumps all English docs from v2.1.97 to v2.1.101, adds mandatory Sources
footer block (previously missing), and documents three new features
shipped between v2.1.98 and v2.1.101:
- /team-onboarding (v2.1.101) — new built-in command for generating
teammate ramp-up guides. Added to 01-slash-commands and CATALOG.
- /ultraplan (v2.1.91+, cloud-env auto-creation in v2.1.101) — full
section in 09-advanced-features covering launch methods, status
indicators, and execution options. Replaces prior 3-line stub.
- Monitor tool (v2.1.98) — full section in 09-advanced-features with
stream-filter and poll-emit patterns and the grep --line-buffered
warning. Added to resources.md feature table.
Vietnamese and Chinese translations are not touched in this sync.
* fix(docs): address review feedback on v2.1.101 sync
- Correct /team-onboarding availability date (April 10 → April 11, 2026)
- Fix uninitialized \$last variable in Monitor poll-and-emit example
- Update CATALOG.md New Features heading to April 2026 and add Monitor
Tool, /team-onboarding, and Ultraplan auto-create entries
The latest Claude Code release is 2.1.97, not 2.3.0 (which is this
guide's own version). Update all 20 "Claude Code Version" footer lines
to accurately reflect the documented Claude Code version.
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
Update all documentation footers from generic "April 2026 / 2.1+" to
the specific sync date (April 9, 2026) and documented version (2.3.0).
Also add version/date footers to zh/CATALOG.md and
zh/01-slash-commands/README.md which were missing them.
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
P0 Critical:
- Remove /vim (removed in v2.1.92) from CATALOG.md, zh/CATALOG.md active tables
- Move /vim to deprecated section in zh/01-slash-commands/README.md
- Fix fake hook events (PreCommit/PrePush/PostPush) in config-examples.json
- Replace with real PreToolUse hook pattern
- Update deprecated model IDs: claude-sonnet-4-5 → claude-sonnet-4-6 (x4)
- Fix notify-team.sh comment: PostPush → PostToolUse with explanation
- Mark # memory shortcut as discontinued in 02-memory/README.md
P2 Conflicts resolved:
- effort:max confirmed valid in current CLI; no changes needed
- Remove WebSocket MCP transport (not supported; only stdio/sse/http valid)
from 05-mcp/README.md, CATALOG.md, QUICK_REFERENCE.md
P4 Cosmetic:
- Update hook count 25 → 26 in QUICK_REFERENCE.md
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
* docs: sync all tutorials with latest Claude Code official docs (April 2026)
Update 44 documentation files to reflect the latest Claude Code features
from code.claude.com. Key content changes include new slash commands
(/ultraplan, /powerup, /sandbox), deprecated command removals (/pr-comments,
/vim), corrected skill description budget (1%/8K), new hook events
(PermissionDenied, InstructionsLoaded, ConfigChange), expanded Agent Teams
section, new plugin components (LSP, bin/, settings.json), and new CLI
flags (--bare, --tmux, --effort, --channels). Added "Last Updated: April
2026" metadata footer to all documentation files.
* fix(docs): correct env var values and alphabetical ordering
- CLAUDE_CODE_NEW_INIT=true → =1 in 02-memory and 09-advanced-features
- CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=true → =1 in 09-advanced-features
- Fix /powerup vs /plugin alphabetical order in slash commands table
* fix(docs): correct env var values in locale files (vi, zh)
Propagate CLAUDE_CODE_NEW_INIT=true → =1 and
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=true → =1 corrections
to Vietnamese and Chinese translations.
* fix(hooks): make hook scripts compatible with Windows Git Bash and use stdin JSON protocol
- Replace `grep -P` (Perl regex) with `sed` for JSON field extraction,
as Windows Git Bash does not support `grep -P`
- Replace positional arg (`$1`) with stdin JSON parsing to match the
actual Claude Code hook protocol (hooks receive data via stdin, not args)
- Fix JSON double-quote escaping in grep patterns that silently fails
on Windows Git Bash
- Remove python3 dependency for JSON parsing, making scripts portable
- Add Windows Git Bash to compatibility notes in script headers
Affected scripts: security-scan.sh, validate-prompt.sh, log-bash.sh, format-code.sh
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(hooks): address review issues in Windows Git Bash compatibility scripts
- security-scan.sh: wrap output in hookSpecificOutput format required by
PostToolUse protocol; restore secret/token detection pattern that was
dropped; escape file path and issues for safe JSON construction
- validate-prompt.sh: extract "user_prompt" field first (Claude Code
UserPromptSubmit protocol), falling back to "prompt"
- log-bash.sh: document sed truncation limitation for commands with
double-quoted strings
- format-code.sh: fix misleading comment about updatedInput output
* fix(hooks): produce valid JSON from security-scan.sh
- Use \\n (JSON newline escape) when building ISSUES, not real newlines,
so the value passes safely through printf into the JSON string
- Remove the real-newline-to-\\n sed pass (no longer needed)
- Output is now verifiably valid JSON per python3 json.loads
* fix(hooks): fix grep -E POSIX compat and semgrep/trufflehog stdout mixing
- Replace \s with [[:space:]] in grep -E patterns (security-scan.sh lines
34,44): \s is a Perl extension, silently fails on macOS BSD grep and
BusyBox — password/secret detection was a no-op on macOS
- Suppress stdout of semgrep/trufflehog (>/dev/null) to prevent their
output mixing with hookSpecificOutput JSON, which would produce invalid
JSON and cause the additionalContext to fail parsing
- Fix format-code.sh hook comment: PreToolUse → PostToolUse (matches
README example and actual hook behavior)
---------
Co-authored-by: Bruce <binyuli1993@foxmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add performance-optimizer subagent and dependency-check hook
Agent-Logs-Url: https://github.com/khanhnkq/claude-howto/sessions/ef3fb01c-a9c0-466e-9ad2-f255f306add2
Co-authored-by: khanhnkq <180888435+khanhnkq@users.noreply.github.com>
* fix(hooks): use basename for manifest matching in dependency-check.sh
FILE=$1 receives an absolute path (e.g. /home/user/project/package.json).
The case statement and all [[ "$FILE" == ... ]] guards matched bare filenames,
so every invocation would hit the *) exit 0 branch and skip all vuln scans.
Extract BASENAME=$(basename "$FILE") and use it for all pattern matching.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Luong NGUYEN <luongnv89@gmail.com>
* feat: add missing pre-tool-check.sh hook to 06-hooks
The LEARNING-ROADMAP.md (Milestone 2A) referenced this file in an
exercise that copies it to ~/.claude/hooks/, but the file did not exist.
This caused confusion for learners following the guide.
The new pre-tool-check.sh is a PreToolUse hook for the Bash matcher that:
- Blocks unconditionally destructive commands (rm -rf /, dd, fork bomb, etc.)
- Warns on high-risk commands (rm -rf, git push --force, DROP TABLE, etc.)
- Reads tool input JSON from stdin (matching Claude Code hook protocol)
- Requires no external dependencies (pure bash + grep)
Fixes#32
* fix(hooks): correct exit code, remove set -e, use portable sed in pre-tool-check.sh
- Change `exit 1` to `exit 2` so Claude Code actually blocks the command
(exit 1 is treated as a non-blocking error; exit 2 is required to block)
- Remove `set -euo pipefail`: `set -e` caused the script to exit on the
first non-matching grep result, skipping all remaining pattern checks
- Replace non-portable `grep -o '"command"\s*:\s*"[^"]*"'` with
`sed -n 's/.*"command"[[:space:]]*:[[:space:]]*"\([^"]*\)".*/\1/p'`
which works on both macOS (BSD) and Linux without GNU grep extensions
Closes#32
---------
Co-authored-by: Luong NGUYEN <luongnv89@gmail.com>
- Replace `grep -P` (Perl regex) with `sed` for JSON field extraction,
as Windows Git Bash does not support `grep -P`
- Replace positional arg (`$1`) with stdin JSON parsing to match the
actual Claude Code hook protocol (hooks receive data via stdin, not args)
- Fix JSON double-quote escaping in grep patterns that silently fails
on Windows Git Bash
- Remove python3 dependency for JSON parsing, making scripts portable
- Add Windows Git Bash to compatibility notes in script headers
Affected scripts: security-scan.sh, validate-prompt.sh, log-bash.sh, format-code.sh
Co-authored-by: Bruce <binyuli1993@foxmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Remove the auto-adapt-mode PostToolUse hook (no more dynamic permission
learning). Replace with a standalone setup script that seeds ~67 safe
auto-mode-equivalent permission rules into settings.json in one shot.
Move the script to 09-advanced-features/ alongside the Auto Mode docs.
Adds a PostToolUse hook that automatically generalizes approved tool
invocations into reusable permission rules in settings.json. Seeds
auto-mode-equivalent baseline permissions on first run. Dangerous
commands (rm -rf, force-push, DROP TABLE, sudo, etc.) are never remembered.
Update 23 files across all 10 tutorial directories and 7 reference
documents to match the latest Claude Code v2.1+ features and correct
outdated content including model names (4.5→4.6), permission modes,
hook events, CLI syntax, MCP config paths, plugin manifest format,
checkpoint commands, session management, and URLs. Add documentation
for new features: Auto Memory, Remote Control, Web Sessions, Desktop
App, Agent Teams, MCP OAuth, Task List, Sandboxing, and more.
- Update all main markdown files (INDEX.md, LEARNING-ROADMAP.md, QUICK_REFERENCE.md, CONTRIBUTING.md, claude_concepts_guide.md, resources.md) with new responsive picture element
- Add logo to all subdirectory README files in feature folders (01-10) and plugins
- Replace old markdown image syntax with HTML picture element for dark/light mode adaptation
- Logo automatically displays dark mode version when system prefers dark mode
- Maintain correct relative paths for all nesting levels (../, ../../, etc.)
- Update README.md with new logo syntax
All markdown files now use the new V2.0 starburst logo design with professional dark/light mode support.
- Replace simple Stop-only context-usage hook with hook pair pattern
- Add UserPromptSubmit + Stop hook combination for tracking delta
- Include both char-estimation and tiktoken versions as separate files
- Show how to use session_id for isolated state tracking
The hook was converting total_chars to string before calculating tokens,
resulting in ~0 tokens reported. Fixed to calculate directly from char count.
- Remove unused estimate_tokens() function
- Calculate tokens as total_chars // 4 directly
- Archive fix-context-usage-hook change
Add Example 6 showing how to create a hook that reports context/token
usage after each Claude response:
- Python script reads transcript_path to access conversation history
- Estimates tokens using ~4 chars/token heuristic
- Outputs one-line report: "Context: ~45k/200k tokens (77% remaining)"
- Documents both Stop and UserPromptSubmit hook configurations
- Explains limitations (estimate vs exact /context command)
Luong NGUYEN