ccc-upgrade

ccc-upgrade is a skill for Claude Code from KevinZai/commander. It costs 36 tokens per session (2,206 once invoked), scanned A, original, MIT.

A maintainer tool for checking and updating Git submodules stored under a project's vendor directory. A submodule is a linked copy of another Git repository.

In plain words
What is it for?
Use it to audit vendor submodules, compare current and latest commits, choose updates, run tests, and commit each approved update.
Why use it?
It shows which vendor repositories have newer commits and helps update selected ones without losing track of the changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/audit-frontmatter.js --check.

Good fit Use it to audit vendor submodules, compare current and latest commits, choose updates, run tests, and commit each approved update.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

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

Made for: Claude Code.

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-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinzai/commander/ccc-upgrade.svg)](https://agentmods.dev/skills/kevinzai/commander/ccc-upgrade)
Your own site
<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-upgrade"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-upgrade.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,206 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 4
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Rogue Agent · line 198
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 5.1 $0.00036 $0.02206
Opus 5 $0.00018 $0.01103
Sonnet 5 $0.00007 $0.00441
Haiku 4.5 $0.00004 $0.00221

Measured 4d ago against content hash 87b6ce5cac23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ccc-upgrade 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-upgrade/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$ccc-upgrade — Vendor Submodule Updater

🔎 Looking to update the CC Commander plugin itself (not this repo's vendor submodules)? That's $ccc-update — a different, end-user-facing tool with a similarly-spelled name. This skill is maintainer-only.

⚠️ Run only from the CC Commander repo root. Verify pwd ends in /cc-commander (or your fork's name) and ls .claude-plugin/marketplace.json succeeds. Running this skill in the wrong cwd would touch unrelated submodules.

Interactive workflow that audits the 19+ vendor submodules under vendor/, surfaces what changed upstream, lets the user pick which to update via AskUserQuestion, then runs the update + test + commit cycle one submodule at a time.

Similar in spirit to $ccc-doctor (read-only diagnostic) — this one writes (commits per submodule) but only after explicit user approval.

When to fire

User types $ccc-upgrade, or says any of:

  • "update vendors"
  • "refresh submodules"
  • "pull latest vendor changes"
  • "sync the ecosystem"
  • "are any vendors out of date"
  • "check vendor drift"

Args:

  • --check — read-only audit (no fetch, no update, no commit)
  • --all — skip the picker and update every submodule with available updates

Steps (always in this order)

1. Locate the repo root + sanity check

Resolve repo root via git rev-parse --show-toplevel. If that fails, output: "Not in a git repo — $ccc-upgrade only works inside the cc-commander checkout." and exit.

Before proceeding, verify you are at the cc-commander repo root:

# Guard: must be at the cc-commander repo root
if [ ! -f ".claude-plugin/marketplace.json" ]; then
  echo "❌ Not at cc-commander repo root. Refusing to update vendor submodules."
  exit 1
fi

If the guard fails, output the error message and exit.

Verify vendor/ exists:

test -d vendor || echo "no-vendor-dir"

If missing, output: "No vendor/ directory at repo root — nothing to upgrade." and exit.

2. List submodules

git submodule status

Read the full file on GitHub · 213 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 · 213 lines · 36 tokens per session scan A 87b6ce5cac23

Subscribe to this mod's changes

ccc-upgrade is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,206 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 2026-09-03.

Related

Other skills, from other repositories

hotfix

Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.

skullninja/coco-workflow · 36 tokens

git-flow

Use when creating a branch, using worktrees for parallel work, committing, or wrapping up. Covers branch naming, conventional commits, short-lived branches, worktree isolation, and final merge/cleanup.

chipfighter/coding-discipline · 43 tokens

justone

Runtime contract for the Just One Prompt Challenge. Invoked exclusively via the /justone and /justone-publish slash commands. Do NOT auto-trigger from general conversation — only act on this skill when one of those commands has been issued in the current turn.

GodsB1025/justone · 55 tokens

fleet-release

Use this skill whenever the user wants to release, ship, prep, or cut versions for two or more plugins together on the current branch. Trigger on phrasings like "release both plugins", "ship them together", "release all changed plugins", "fleet release", "multi-plugin release", "release in order", or "release…

gtapps/claude-code-hermit · 96 tokens

changelog

A tool for writing release notes from a structured record of changes that actually shipped. Release notes summarize changes for people who use or maintain the product.

qwerfunch/cladding · 121 tokens

rollback

Record a rollback event and print the maintainer-runnable git command for the most recent checkpoint of a feature. Use when an implementation attempt failed, an autonomous drive loop hit RETRYTHRESHOLD, or the user wants to abandon the current attempt and restore the pre-checkpoint state. Activate only when the…

qwerfunch/cladding · 80 tokens