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/unicomai/wanwu/customizenpx skills add UnicomAI/wanwu --skill customizegit clone --depth 1 https://github.com/UnicomAI/wanwuWhat 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 | $0.00088 | $0.05336 |
| Opus 5 | $0.00044 | $0.02668 |
| Sonnet 5 | $0.00018 | $0.01067 |
| Haiku 4.5 | $0.00009 | $0.00534 |
Grade A, and why
customize scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
return subprocess.run([sys.executable, tool, cfg_path], How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customize
Build and maintain agent profiles and skills programmatically via the
repl tool using host.agents.* and host.skills.*.
A profile is a named bundle that shapes how an agent behaves:
system_prompt— the profile's identity. This is the opening of the agent's system prompt; it REPLACES the generic "You are Claude Science" base identity. Write it in second person, lead withYou are {display_name}, ..., state what the agent specializes in and what it does NOT do. Everything else (tool-usage rules, working-style bullets, scope guardrail) is inherited automatically — don't restate it.display_name/description/icon_key/color_key— picker metadata.skill_names(optional restriction) — by default a profile sees the full live skill catalog viasearch_skills/skill(...), same as the main agent. Pass an explicit list ONLY to deliberately restrict it;[]creates a zero-skill specialist. Restricting skills also restricts connectors — a singleunrestrictedflag governs both; passingskill_namesflips the profile to curated mode and starts it with zero connectors (see next).- Connector access — an unrestricted profile (the default) reaches
every connector (bundled + custom + authorized directory), same as the
main agent; use
detach_connectorto subtract specific ones. A curated profile (one created with an explicitskill_nameslist, or flipped via{"unrestricted": False}) starts with no connectors — reach is exactly what youattach_connector. excludedTools— per-tool blocklist applied after connectors resolve. Use to strip specific high-risk or irrelevant tools from an otherwise-useful connector. Per-connector, not a profile field — set viaattach_connector(..., include_tools_pattern=/exclude_tools_pattern=); the profile'sexcludedToolsinlist()is the read-only aggregation across all its attached connectors. Patterns match the connector's bare tool names (e.g.'^list_marts$', as returned bylist_connectors(name)['tools']); the aggregatedexcludedToolsentries are stored fully-qualified asmcp_<connector>_<tool>since the list spans every attached connector.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 458 lines · 88 tokens per session scan A af31c7054522
customize is a skill published in the GitHub repository UnicomAI/wanwu (2,452 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 88 tokens to every session and 5,336 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
project-orchestration
Orchestrate multi-agent workflows for feature development using planning agents, context handoff, and stage management.
ccg-skills
CCG Skills - Quality gates, documentation generator, and multi-agent orchestration. Auto-installed by CCG workflow system.
ai
AI/LLM 能力索引。Agent 开发、LLM 安全、RAG 系统。当用户提到 AI、LLM、Agent、RAG、Prompt 时路由到此。.
orchestration
协同编排知识域。多Agent协同、任务分解、并行执行、冲突解决。当魔尊需要多Agent协作、任务编排、并行处理时使用。.
workflow-creation
Create a new Stencila workflow. Use when asked to create, write, scaffold, or set up a workflow directory or WORKFLOW.md file. Covers workflow discovery, duplicate-name checks, ephemeral workflows, WORKFLOW.md frontmatter, DOT pipeline authoring, goals, agents, branching, composition, and validation.