Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/leejuoh/claude-code-zero/claw-mo-setupnpx skills add LeeJuOh/claude-code-zero --skill claw-mo-setupgit clone --depth 1 https://github.com/LeeJuOh/claude-code-zeroWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.01241 |
| Opus 5 | $0.00022 | $0.00620 |
| Sonnet 5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
claw-mo-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claw-mo-setup
Configure mo markdown viewer with group-based watch patterns for the current project.
For config schema, port logic, and groups: read ${CLAUDE_PLUGIN_ROOT}/references/shared.md
Steps
-
Prerequisites check
command -v mo >/dev/null 2>&1→ if missing:brew install k1LoW/tap/mo, stop- If
$CMUX_SURFACE_IDis not set: mention that cmux (https://cmux.dev) provides a built-in browser panel alongside the terminal — ideal for viewing docs while coding. Brief one-liner, don't push.
-
Detect project root:
git rev-parse --show-toplevel(fallback:$PWD) -
Check existing config: Read
${CLAUDE_PLUGIN_DATA}/config.json. If an entry exists for this project:- Show current groups and port
- Ask: "Config already exists — update existing groups or start fresh?"
- Update: Skip to step 6 with current groups pre-populated (user can add/remove/rename)
- Start fresh: Continue from step 4
-
Scan markdown files:
find "$PROJECT_ROOT" -name '*.md' -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/vendor/*' 2>/dev/null | wc -lWarn if 500+.
-
List directories with .md files:
find "$PROJECT_ROOT" -name '*.md' -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/vendor/*' 2>/dev/null | sed "s|$PROJECT_ROOT/||" | cut -d/ -f1 | sort -u -
Suggest groups based on the directories found in step 5:
- For each directory found, get the file count and suggest a group named after that directory:
find "$PROJECT_ROOT/DIRNAME" -name '*.md' -not -path '*/node_modules/*' -not -path '*/.git/*' -not -path '*/vendor/*' 2>/dev/null | wc -l - If a top-level directory is huge, do not blindly suggest
DIRNAME/**/*.md. Inspect one level deeper and propose narrower subgroups when that better matches the actual content (for exampleraw/articles/**/*.mdbut notraw/**/*.mdwhenraw/repos/**dominates) - If root
.mdfiles exist, suggest groupdefaultwith*.md - Use the actual directory name as the group name — don't rename or merge unless obvious (e.g., a single top-level dir with 1 file might be skipped)
- Always show file counts so the user can see what each pattern covers, and explicitly call out directories you are excluding because the watch scope would be too large
- For each directory found, get the file count and suggest a group named after that directory:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 75 lines · 44 tokens per session scan A 74a21e842145
claw-mo-setup is a skill published in the GitHub repository LeeJuOh/claude-code-zero (51 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,241 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.