ccc-more

ccc-more is a skill for Claude Code, Codex from KevinZai/commander. It costs 43 tokens per session (1,581 once invoked), scanned A, original, MIT.

A second-page menu for CC Commander, grouping tools for planning, project inspection, Linear, agent fleets, connections, and browsing the catalogue. It also shows basic project context such as the current branch and open tasks.

In plain words
What is it for?
Use it to open planning and inspection tools, manage agent fleets, connect services, browse available tools, or check basic project setup.
Why use it?
It makes less frequently used tools discoverable without requiring users to remember every command.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

Install

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.

agentmods
npx agentmods add skills/kevinzai/commander/ccc-more
Any agent
npx skills add KevinZai/commander --skill ccc-more
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ccc-more

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinzai/commander/ccc-more.svg)](https://agentmods.dev/skills/kevinzai/commander/ccc-more)
Your own site
<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-more"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-more.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.01581
Opus 5 $0.00022 $0.00790
Sonnet 5 $0.00009 $0.00316
Haiku 4.5 $0.00004 $0.00158

Measured 4d ago against content hash 1a0e794c00de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccc-more 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 4d 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.

commander/cowork-plugin-codex/skills/ccc-more/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$ccc-more — Second-page tools menu

Click-first picker for the CC Commander surface area that's NOT build/review/ship/design/learn. Plan, x-ray, Linear, fleet, connect, browse — one click each, cascade for the long tail.

Response shape (EVERY time)

1. Brand header (one line)

**CC Commander · More** · 7 tools · [all commands](https://commanderplugin.com/commands)

2. Context strip (one line)

Parallel Bash probe (silent on failure):

  • test -f tasks/todo.md && wc -l tasks/todo.md — open tasks
  • git rev-parse --abbrev-ref HEAD 2>/dev/null — branch
  • claude mcp list 2>/dev/null | grep -c '^ ' — connected MCPs
  • test -f .linear/config.json && echo linear-ok — Linear wired

Render:

🧭 Branch <name> · open tasks · MCPs connected · Linear: <connected | not set up>

If barely any context: "🧭 Empty-ish project — Plan a feature or run X-ray to get signal."

3. The picker — AskUserQuestion page 1

Read ${CLAUDE_PLUGIN_ROOT}/menus/ccc-more.json once. Use its choices. Max 4 options — 3 headline tools + "Even more…".

question: "Which tool?"
header: "CC Commander · More"
multiSelect: false
options:
  - label: "📋 Plan a feature"
    description: "Spec interview → implementation plan file → review checkpoint."
    preview: "Invokes ccc-plan. Asks 5-7 targeted questions — writes to the session plan file (shows in Desktop Plan pane)."
  - label: "🩻 Project x-ray"
    description: "Scorecard across code, docs, tests, deps, CI — actionable findings."
    preview: "Invokes ccc-xray. Reads repo, returns report card + remediation steps."
  - label: "📊 Linear board"
    description: "View, pick, or create issues without leaving Claude."
    preview: "Invokes ccc-linear. Requires Linear MCP; will prompt $ccc-connect if missing."
  - label: "⋯ Even more…"
    description: "Fleet, connect apps, browse catalog."
    preview: "3 more tools — click to cascade."

Recommendation logic (prepend ⭐ to ONE option):

  • No tasks/ dir and no CLAUDE.md → ⭐ "Plan a feature"
  • Repo >500 files or messy tests → ⭐ "Project x-ray"
  • Linear MCP connected + current branch matches cc-<num>-* → ⭐ "Linear board"
  • Nothing special → ⭐ "Plan a feature"

Read the full file on GitHub · 142 lines

Changes

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.

  1. 4d ago First seen · 142 lines · 43 tokens per session scan A 1a0e794c00de

Subscribe to this mod's changes

ccc-more is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,581 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.