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/sbusso/claudeclaw/setupnpx skills add sbusso/claudeclaw --skill setupgit clone --depth 1 https://github.com/sbusso/claudeclawWhat 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 | $0.00054 | $0.04914 |
| Opus 5 | $0.00027 | $0.02457 |
| Sonnet 5 | $0.00011 | $0.00983 |
| Haiku 4.5 | $0.00005 | $0.00491 |
Grade F, and why
setup scanned grade F with 4 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
2. Collect credentials/tokens and write to `.env` Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`, or nvm Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Linux: install with `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER`. Note: user may need to log out/in for group membership. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Linux: `curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs`, or nvm How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClaudeClaw Setup
Run setup steps automatically. Only pause when user action is required (channel authentication, configuration choices). Setup uses bash setup.sh for bootstrap, then npx tsx setup/index.ts --step <name> for all other steps. Steps emit structured status blocks to stdout. Verbose logs go to logs/setup.log.
Principle: When something is broken or missing, fix it. Don't tell the user to go fix it themselves unless it genuinely requires their manual action (e.g. authenticating a channel, pasting a secret token). If a dependency is missing, install it. If a service won't start, diagnose and repair. Ask the user for permission when needed, then do the work.
UX Note: Use AskUserQuestion for all user-facing questions.
Mode Detection
Before any steps, detect the execution mode:
cat .claude-plugin/plugin.json 2>/dev/null | grep '"name": "claudeclaw"' && echo "DEVELOPER_MODE" || echo "PLUGIN_MODE"
If .claude-plugin/plugin.json exists in the current directory AND contains "name": "claudeclaw", we're inside the ClaudeClaw repo → Developer mode. Otherwise, the skill was loaded via --plugin-dir → Plugin mode.
Directory = Instance model
The current working directory IS the ClaudeClaw instance. All state (.env, store/, groups/, logs/) lives in cwd. Multiple instances = multiple directories. No hidden state, no ~/.claude/plugin-data/.
Plugin mode (no .claude-plugin/ in cwd):
- Skip step 0 (Git & Fork) entirely
- The current directory is the data directory — all state goes here
- Plugin code directory:
${CLAUDE_PLUGIN_ROOT} - Ensure data directories exist:
mkdir -p store groups logs - Check for
.claudeclaw.json— if it exists, this directory has been set up before; if not, this is a fresh setup
CRITICAL — Plugin mode command prefix: All npx tsx setup/index.ts commands in subsequent steps MUST be run from the plugin code directory with CLAUDE_PLUGIN_ROOT set, but the working directory for the service must be the USER's current directory (the data dir). Use this pattern:
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 · 379 lines · 54 tokens per session scan F 8ebd6ddd0857
setup is a skill published in the GitHub repository sbusso/claudeclaw (193 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 4,914 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it F with 4 findings (harvests environment variables, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hello
Sample knowledge-only skill demonstrating the SKILL.md layout.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
explain-for
Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground…
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.