ccmanager-config

ccmanager-config is a skill for Claude Code from kbwo/ccmanager. It costs 123 tokens per session (1,453 once invoked), scanned A, original, MIT.

Set up, review, or repair a CCManager config — .ccmanager.json at a git repository root, or the global /.config/ccmanager/config.json. Use when someone wants ccmanager to launch a different agent CLI (codex, gemini, cursor-agent, copilot…), add command presets, run a command on session state changes or worktree…

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the ccmanager-config plugin — 1 skill shipped together

Install with agentmods
npx agentmods add skills/kbwo/ccmanager/ccmanager-config
About the project

CCManager is a command-line application for managing multiple sessions of AI coding assistants across Git worktrees and projects. It is for developers working with tools such as Claude Code, Gemini CLI, Codex CLI, Cursor Agent, Copilot CLI, Cline CLI, OpenCode, and Kimi CLI, and the catalogue entries provide commands and instructions for its workflows.

kbwo/ccmanager · 1,234 stars · on GitHub

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.

Any agent
npx skills add kbwo/ccmanager --skill ccmanager-config
Clone the repo
git clone --depth 1 https://github.com/kbwo/ccmanager

Made for: Claude Code.

Or install ccmanager-config, the plugin that ships this one along with the rest of its 1 skill.

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 ccmanager-config

README.md
[![agentmods](https://agentmods.dev/badge/skills/kbwo/ccmanager/ccmanager-config.svg)](https://agentmods.dev/skills/kbwo/ccmanager/ccmanager-config)
Your own site
<a href="https://agentmods.dev/skills/kbwo/ccmanager/ccmanager-config"><img src="https://agentmods.dev/badge/skills/kbwo/ccmanager/ccmanager-config.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 5.1 $0.00123 $0.01453
Opus 5 $0.00062 $0.00727
Sonnet 5 $0.00025 $0.00291
Haiku 4.5 $0.00012 $0.00145

Measured today against content hash cc020c8dcc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ccmanager-config 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate-ccmanager-config.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ccmanager-config/skills/ccmanager-config/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configuring CCManager

CCManager (ccmanager) is a terminal UI that runs one AI coding agent per git worktree. Its behaviour comes from two JSON files with identical shape:

File Scope Notes
<git repository root>/.ccmanager.json one repository commit it to share with the team
~/.config/ccmanager/config.json (%APPDATA%\ccmanager\config.json on Windows) the user, all repositories also written by ccmanager's own Global Configuration menu

Per key, the project file wins over the global file. Both are optional.

The reason this skill exists: CCManager reports nothing when a config is wrong. A file that is not valid JSON is discarded whole, and unknown keys are ignored without a message, so a typo is indistinguishable from a feature that does not work. Every change made through this skill therefore ends with the validator run in step 4.

Procedure

1. Decide which file to edit

Ask yourself, and the user if it is genuinely ambiguous:

  • Does the setting describe the repository (which agent CLI to run, what to do after a worktree is created, where worktrees live)? → .ccmanager.json, committed.
  • Does it describe this person's machine or taste (notification commands, key bindings, personal API/model flags)? → the global config.json.

Two traps before you write anything:

  • Put .ccmanager.json at the main repository root, not inside a linked worktree. CCManager resolves any worktree back to the main checkout, so a config file inside a worktree is never read.
  • If ccmanager is started in multi-project mode (the CCMANAGER_MULTI_PROJECT_ROOT environment variable is set, or --multi-project is passed), project files are skipped entirely and only the global config applies. Say so rather than writing a file that will be ignored.

2. Read what is already there

cat the target file if it exists, plus the other file in the pair when the user's request depends on the merged result. Never rewrite a config from scratch when one exists — you would silently drop settings you were not asked about.

Read the full file on GitHub · 124 lines

Files

What ships with it

4 files 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.

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. today First seen · 124 lines · 123 tokens per session scan A cc020c8dcc7f

Subscribe to this mod's changes

ccmanager-config is a skill published in the GitHub repository kbwo/ccmanager (1,234 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 1,453 once invoked, about $0.0006 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 2026-09-06.