wenlan-app/wenlan
A studio for everything you think, learn, and build with AI. It gathers notes and memories from every AI tool into pages, skills and rules that stay current and fully customizable. Open source. For you and your team.
field: AI / MLProductivity workflow: Git & commitsDocsPR / code reviewSecurity reviewCI/CD & deploy runs claude in CI
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~6.5k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 18/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit wenlan-app/wenlan/.claude ./rig-wenlan # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit wenlan-app/wenlan/.claude/skills/prove .claude/skills/prove $ npx degit wenlan-app/wenlan/.claude/skills/run-wenlan-app .claude/skills/run-wenlan-app $ npx degit wenlan-app/wenlan/.claude/skills/run-wenlan .claude/skills/run-wenlan $ npx degit wenlan-app/wenlan/.claude/skills/verify .claude/skills/verify $ npx degit wenlan-app/wenlan/plugin-agents/skills/wenlan-brief .claude/skills/wenlan-brief $ npx degit wenlan-app/wenlan/plugin-agents/skills/wenlan-capture .claude/skills/wenlan-capture $ npx degit wenlan-app/wenlan/plugin-agents/skills/wenlan-handoff .claude/skills/wenlan-handoff $ npx degit wenlan-app/wenlan/plugin-agents/skills/wenlan-how-i-work .claude/skills/wenlan-how-i-work $ npx degit wenlan-app/wenlan/plugin-agents/skills/wenlan-recall .claude/skills/wenlan-recall $ npx degit wenlan-app/wenlan/plugin-agents/skills/wenlan .claude/skills/wenlan $ npx degit wenlan-app/wenlan/plugin-codex/skills/brief .claude/skills/brief $ npx degit wenlan-app/wenlan/plugin-codex/skills/capture .claude/skills/capture $ npx degit wenlan-app/wenlan/plugin-codex/skills/handoff .claude/skills/handoff $ npx degit wenlan-app/wenlan/plugin-codex/skills/how-i-work .claude/skills/how-i-work $ npx degit wenlan-app/wenlan/plugin-codex/skills/recall .claude/skills/recall $ npx degit wenlan-app/wenlan/plugin/skills/curate .claude/skills/curate $ npx degit wenlan-app/wenlan/plugin/skills/forget .claude/skills/forget $ npx degit wenlan-app/wenlan/plugin/skills/lint .claude/skills/lint $ npx degit wenlan-app/wenlan/plugin/skills/pages .claude/skills/pages $ npx degit wenlan-app/wenlan/plugin/skills/setup .claude/skills/setup $ npx degit wenlan-app/wenlan/plugin/skills/steep .claude/skills/steep $ npx degit wenlan-app/wenlan/plugin/skills/theme .claude/skills/theme $ npx degit wenlan-app/wenlan/plugin/skills/wiki .claude/skills/wiki
$ curl -fsSL --create-dirs -o .claude/agents/doc-drift-auditor.md https://raw.githubusercontent.com/wenlan-app/wenlan/main/.claude/agents/doc-drift-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/eval-skew-reviewer.md https://raw.githubusercontent.com/wenlan-app/wenlan/main/.claude/agents/eval-skew-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/rust-async-safety-reviewer.md https://raw.githubusercontent.com/wenlan-app/wenlan/main/.claude/agents/rust-async-safety-reviewer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bash -c 'IN=$(cat); H=.claude/hooks/block-no-verify.sh; C=$(printf %s \"$IN\" | jq -r \".cwd // empty\"); R=\"${CLAUDE_PROJECT_DIR:-}\"; [ -f \"$R/$H\" ] || R=$(git -C \"$C\" rev-parse --show-toplevel 2>/dev/null); if [ -f \"$R/$H\" ]; then printf %s \""
}
]
},
{
"matcher": "Edit|Write|MultiEdit",
"hooks": [
{
"type": "command",
"command": "bash -c 'IN=$(cat); H=.claude/hooks/block-release-please-files.sh; C=$(printf %s \"$IN\" | jq -r \".cwd // empty\"); R=\"${CLAUDE_PROJECT_DIR:-}\"; [ -f \"$R/$H\" ] || R=$(git -C \"$C\" rev-parse --show-toplevel 2>/dev/null); if [ -f \"$R/$H\" ]; then "
}
]
}
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| wenlan | local / custom | 2.5k |
Skills (23)
proverun-wenlan-apprun-wenlanverifywenlan-briefwenlan-capturewenlan-handoffwenlan-how-i-workwenlan-recallwenlanbriefcapturehandoffhow-i-workrecallcurateforgetlintpagessetupsteepthemewiki
Subagents (3)
| doc-drift-auditor model: opus | Read-only audit for fuzzy drift the CI teeth (drift_guard.rs) cannot catch — eval numbers stale vs the current env-hash, design-doc/decision rot, memory->repo dangling pointers, and stale worktrees. R |
| eval-skew-reviewer model: opus | Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND |
| rust-async-safety-reviewer model: opus | Reviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produce |
Hooks (3)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | bash -c 'IN=$(cat); H=.claude/hooks/block-no-verify.sh; C=$(printf %s "$IN" | jq -r ".cwd // empty"); R="${CLAUDE_PROJECT_DIR:-}"; [ -f "$R/$H" ] || R=$(git -C "$C" rev-parse --show-toplevel 2>/dev/null); if [ -f "$R/$H" ]; then printf %s " |
| PreToolUse | Edit|Write|MultiEdit | bash -c 'IN=$(cat); H=.claude/hooks/block-release-please-files.sh; C=$(printf %s "$IN" | jq -r ".cwd // empty"); R="${CLAUDE_PROJECT_DIR:-}"; [ -f "$R/$H" ] || R=$(git -C "$C" rev-parse --show-toplevel 2>/dev/null); if [ -f "$R/$H" ]; then |
| Stop | * | bash -c 'IN=$(cat); H=.claude/hooks/pre-stop-gate.sh; C=$(printf %s "$IN" | jq -r ".cwd // empty"); R="${CLAUDE_PROJECT_DIR:-}"; [ -f "$R/$H" ] || R=$(git -C "$C" rev-parse --show-toplevel 2>/dev/null); if [ -f "$R/$H" ]; then printf %s "$I |
Similar rigs
7xuanlu/wenlan
A living personal wiki. Wenlan turns your documents, notes, and AI chats into pages with links to their sources, and updates them as sources change without overwriting your edits. Claude Code, Codex and other AI tools can build on it.
Skill Collector 5.7k tok · · Q18
serionist/docket
A personal memory and task manager that Claude works in: raw and processed, in your own git repo, local first.
Skill Collector 8.0k tok · · Q19
gagharutyunyan1993/ghorc
Claude Code plugin: an Opus lead plans, Sonnet subagents work, hooks block repeated reads and worker test-suite runs.
Pragmatist 1.2k tok · · Q0
memtomem/memtomem
Long-term memory for AI coding agents, kept as Markdown you own. Hybrid BM25 + vector search over your notes and code via MCP — one local store shared across Claude Code, Codex, Cursor, OpenCode, and more. Hook-free by default.
Skill Collector 4.6k tok · · Q3