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.
git 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/commands/kevinzai/commander/ccc-multi-frontend)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-multi-frontend"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-multi-frontend/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-multi-frontend"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-multi-frontend.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01473 |
| Opus 5.5 | $0.00016 | $0.00589 |
| Sonnet 5.5 | $0.00008 | $0.00295 |
| Haiku 4.5 | $0.00004 | $0.00147 |
Grade A, and why
ccc-multi-frontend 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 5d 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.
This is a copy
97% identical to multi-frontend — 199 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-multi-frontend — Gemini-led frontend workflow
CC Commander · /ccc-multi-frontend · a UI change planned and reviewed with Gemini, written by the assistant.
Usage
/ccc-multi-frontend <UI task description>
Task: $ARGUMENTS. If it is empty, ask the user for the UI task before starting.
Roles:
- Gemini — frontend UI and UX; its frontend opinions are authoritative.
- Codex — backend perspective; treat its frontend opinions as reference only.
- The assistant — orchestration, planning, every file write, and delivery. External models never write to the filesystem.
The user's selected session model is preserved.
Prerequisite: ccg-workflow runtime (opt-in)
This command calls the external ccg-workflow runtime, which Commander does not bundle. Check it first:
test -x ~/.claude/bin/codeagent-wrapper && ls ~/.claude/.ccg/prompts/gemini
If the check fails, ask with AskUserQuestion (Codex: a plain-text question):
- 🟢 Run Claude-only — continue with built-in tools and skip the Gemini calls (use
/ccc-planfor planning) - Install first — point the user to the upstream ccg-workflow installation guide and stop
- Cancel — stop without changes
Gemini call
Run every wrapper call with Bash, run_in_background: true and timeout: 3600000. Add any extra flags your ccg-workflow install documents (for example lite mode) before --backend. Pass --gemini-model <model> with the Gemini model your install documents, or omit it to use the wrapper default.
# New session
~/.claude/bin/codeagent-wrapper --backend gemini --gemini-model <model> - "$PWD" <<'EOF'
ROLE_FILE: <role prompt path>
<TASK>
Requirement: <enhanced requirement, or the original task>
Context: <project context and analysis from previous phases>
</TASK>
OUTPUT: <expected output format>
EOF
# Resume an existing session
~/.claude/bin/codeagent-wrapper --backend gemini --gemini-model <model> resume <SESSION_ID> - "$PWD" <<'EOF'
...same body...
EOF
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.
- 5d ago Changed · -52 lines · +22 tokens per session 0b4357c643ba
- 1mo ago First seen · 163 lines · 17 tokens per session scan A 28c05fc7d581
ccc-multi-frontend is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,473 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to multi-frontend, differing in 199 lines, and is treated as a copy.
Other commands, from other repositories
qa-design
UI/UX design audit and verification of web best practices.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.