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/kevinzai/commander/ccc-consolenpx skills add KevinZai/commander --skill ccc-consolegit clone --depth 1 https://github.com/KevinZai/commanderWhat 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 | $0.00040 | $0.03120 |
| Opus 5 | $0.00020 | $0.01560 |
| Sonnet 5 | $0.00008 | $0.00624 |
| Haiku 4.5 | $0.00004 | $0.00312 |
Grade A, and why
ccc-console 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-console — the Commander Console
The Console lives in your chat. Publishing makes a snapshot page you can keep or share.
One panel instead of four separate decks: who's working, what it cost, what got blocked, what you've done over the last month, and a box you can type into that reaches this session. It reads only your own local telemetry under ~/.claude/commander/ — the same logs $ccc-mission-control, $ccc-usage and $ccc-safety already read, composed once by lib/console-model.js. The one exception is Memory, which reads your own claude-mem store at ~/.claude-mem/ if (and only if) you have one.
🔒 Opening is local. The inline widget renders from local logs and nothing leaves the machine. Publishing is a separate act and always asks first — see below.
How it routes
On $ccc-console with no argument, open the widget on the Overview tab (below). Explicit sub-commands skip straight to their tab or action:
| Argument | What happens |
|---|---|
overview (default) |
agents working, anything awaiting your approval, task counts |
usage |
saved / spent / dispatches, cost by app |
safety |
blocked, auto-fixed, approved, tool-failure hotspots |
memory |
recent claude-mem observation titles + counts — optional, see below |
history |
the last 30 days day by day: cost, dispatches, tasks, failures, top skills |
launch |
one-click chips for the common Commander workflows |
refresh |
re-read the logs and render a fresh widget |
publish |
build the snapshot artifact — consent-gated, see below |
on / off |
turn the session-start auto-open on or off (see below) |
🖥️ Open the console (the default — inline widget)
Build the widget HTML, then render it inline with the visualize MCP's show_widget — not the Artifact tool. This is the whole point of the surface: an inline widget can call the host's sendPrompt(text), so its chips and its prompt bar reach this live session. A published artifact cannot (strict CSP, no completion capability), which is why publishing is a different verb.
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 · 154 lines · 40 tokens per session scan A 05f366b15d69
ccc-console is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 3,120 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 2026-08-31.
Other skills, from other repositories
crewai
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative…
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A…
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
agent-workflow-designer
../../../engineering/skills/agent-workflow-designer/SKILL.md.
ai-security
../../../engineering-team/skills/ai-security/SKILL.md.