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 skills add KevinZai/commander --skill ccc-updategit clone --depth 1 https://github.com/KevinZai/commanderWrote 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.
[](https://agentmods.dev/skills/kevinzai/commander/ccc-update)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-update"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-update.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.02713 |
| Opus 5 | $0.00018 | $0.01357 |
| Sonnet 5 | $0.00007 | $0.00543 |
| Haiku 4.5 | $0.00004 | $0.00271 |
Grade D, and why
ccc-update scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Never tell the user to `git pull` — there is no working tree in a Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
REMOTE_VERSION=$(curl -fsSL --max-time 8 "https://raw.githubusercontent.com/KevinZai/commander/main/commander/cowork-plugin/.claude-plugin/plugin.json" 2>/dev/null | node -e " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
REMOTE_VERSION=$(curl -fsSL --max-time 8 "https://raw.githubusercontent.com/KevinZai/commander/main/commander/cowork-plugin/.claude-plugin/plugin.json" 2>/dev/null | node -e " How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-update — Update CC Commander
CC Commander · $ccc-update · Detect → update → restart → verify
The end-user counterpart to $ccc-doctor (which also detects staleness, but
as one row in a bigger diagnostic report) — this skill does ONE thing:
get the user onto the latest version, correctly, in the fewest steps.
Looking for the vendor-submodule updater instead (
vendor/*git submodules under this repo, maintainer-only)? That's$ccc-upgrade— a different tool with a similarly-spelled name. This skill ($ccc-update) is for end users updating the installed plugin itself.
Step 1 — Detect installed vs latest
CLONE="$HOME/.claude/plugins/marketplaces/commander-hub"
if [ ! -d "$CLONE" ]; then
CLONE=$(node -e "
try {
const d=JSON.parse(require('fs').readFileSync(process.env.HOME+'/.claude/plugins/known_marketplaces.json','utf8'));
const m=d['commander-hub'];
if(m&&m.installLocation) process.stdout.write(m.installLocation);
} catch(e) {}
" 2>/dev/null || echo "")
fi
[ -z "$CLONE" ] && CLONE="n/a"
[ "$CLONE" != "n/a" ] && [ ! -d "$CLONE" ] && CLONE="n/a"
INSTALLED_JSON="$HOME/.claude/plugins/installed_plugins.json"
INSTALLED_VERSION="n/a"
if [ -f "$INSTALLED_JSON" ]; then
INSTALLED_VERSION=$(node -e "
try {
const d = JSON.parse(require('fs').readFileSync('$INSTALLED_JSON','utf8'));
const k = Object.keys(d.plugins||{}).find(k => k.startsWith('commander@'));
process.stdout.write(k && d.plugins[k][0] ? (d.plugins[k][0].version||'n/a') : 'n/a');
} catch(e) { process.stdout.write('n/a'); }
" 2>/dev/null || echo "n/a")
fi
# Desktop-managed (account-synced) install: Cowork/Claude Desktop provisions the
# plugin under Application Support per session — NO marketplace clone and NO
# installed_plugins.json entry exist in that mode. Detect it and read its version.
DESKTOP_VERSION="n/a"
if [ "$CLONE" = "n/a" ] && [ "$INSTALLED_VERSION" = "n/a" ]; then
DESKTOP_MANIFEST=$(/bin/ls -t "$HOME/Library/Application Support/Claude/"local-agent-mode-sessions/*/*/rpm/plugin_*/.claude-plugin/plugin.json 2>/dev/null | head -50 | while read -r f; do
if /usr/bin/grep -q '"name"[[:space:]]*:[[:space:]]*"commander"' "$f" 2>/dev/null; then echo "$f"; break; fi
done)
if [ -n "$DESKTOP_MANIFEST" ]; then
DESKTOP_VERSION=$(node -e "
try { process.stdout.write(JSON.parse(require('fs').readFileSync('$DESKTOP_MANIFEST','utf8')).version||'n/a'); }
catch(e) { process.stdout.write('n/a'); }
" 2>/dev/null || echo "n/a")
fi
fi
# Dev checkout: running inside the cc-commander repo itself (maintainer mode).
DEV_REPO="n/a"
if [ -f "package.json" ] && /usr/bin/grep -q '"name": "cc-commander"' package.json 2>/dev/null; then
DEV_REPO="$(pwd)"
fi
REMOTE_VERSION="n/a"
if [ "$CLONE" != "n/a" ]; then
REMOTE_VERSION=$(node "$CLONE/commander/update-check.js" --remote-only 2>/dev/null || echo "n/a")
else
# No clone to run the checker from — ask GitHub directly (raw manifest on main).
REMOTE_VERSION=$(curl -fsSL --max-time 8 "https://raw.githubusercontent.com/KevinZai/commander/main/commander/cowork-plugin/.claude-plugin/plugin.json" 2>/dev/null | node -e "
let s='';process.stdin.on('data',d=>s+=d).on('end',()=>{try{const v=JSON.parse(s).version;process.stdout.write(/^\d+\.\d+\.\d+$/.test(v)?v:'n/a');}catch(e){process.stdout.write('n/a');}});
" 2>/dev/null || echo "n/a")
fi
echo "CLONE=$CLONE"
echo "INSTALLED_VERSION=$INSTALLED_VERSION"
echo "DESKTOP_VERSION=$DESKTOP_VERSION"
echo "DEV_REPO=$DEV_REPO"
echo "REMOTE_VERSION=$REMOTE_VERSION"
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.
- 4d ago First seen · 214 lines · 37 tokens per session scan D b719d43ea38a
ccc-update is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 2,713 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (subtle steering, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
multi-plan-handoff
Auto-detect plan files in conversation context and pass them to multi: execute subagents by reference, not by paraphrase.
skill-dev
Use this skill when creating or refining Claude Code skill definitions. Skills are model-invoked capabilities that Claude activates autonomously based on context. Helps design focused skills with discovery-optimized descriptions, proper directory structures, and supporting resources. Automatically invoked when user…
command-dev
Use this skill when creating or refining custom Claude Code slash commands. Slash commands are user-invoked reusable prompts that can accept arguments, reference files, and execute bash operations. Helps design command syntax, argument handling, file references, bash execution, and frontmatter configuration.…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…