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-backend)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-multi-backend"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-multi-backend/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-backend"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-multi-backend.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 | $0.00040 | $0.01459 |
| Opus 5.5 | $0.00016 | $0.00584 |
| Sonnet 5.5 | $0.00008 | $0.00292 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
ccc-multi-backend 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 6d 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
94% identical to multi-backend — 198 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-multi-backend — Codex-led backend workflow
CC Commander · /ccc-multi-backend · a backend change planned and reviewed with Codex, written by the assistant.
Usage
/ccc-multi-backend <backend task description>
Task: $ARGUMENTS. If it is empty, ask the user for the backend task before starting.
Roles:
- Codex — backend logic and algorithms; its backend opinions are authoritative.
- Gemini — frontend perspective; treat its backend opinions as reference only.
- The assistant — orchestration, planning, every file write, and delivery. External models never write to the filesystem.
The user's selected session model is preserved. Codex runs on the model set in the user's Codex config; Commander's default executor is gpt-6.1-sol and gpt-6-astra suits the review pass.
Prerequisite: ccg-workflow runtime (opt-in)
This command calls the external ccg-workflow runtime, which Commander does not bundle. Check it first:
test -x ~/.claude/bin/codeagent-wrapper && ls ~/.claude/.ccg/prompts/codex
If the check fails, ask with AskUserQuestion (Codex: a plain-text question):
- 🟢 Run Claude-only — continue with built-in tools and skip the Codex calls (use
/ccc-planfor planning) - Install first — point the user to the upstream ccg-workflow installation guide and stop
- Cancel — stop without changes
Codex call
Run every wrapper call with Bash, run_in_background: true and timeout: 3600000. Add any extra flags your ccg-workflow install documents (for example lite mode) before --backend.
# New session
~/.claude/bin/codeagent-wrapper --backend codex - "$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 codex resume <SESSION_ID> - "$PWD" <<'EOF'
...same body...
EOF
| Phase | Role prompt |
|---|---|
| Analysis | ~/.claude/.ccg/prompts/codex/analyzer.md |
| Planning | ~/.claude/.ccg/prompts/codex/architect.md |
| Review | ~/.claude/.ccg/prompts/codex/reviewer.md |
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.
- 6d ago Changed · -53 lines · +22 tokens per session 181d74feb968
- 1mo ago First seen · 163 lines · 18 tokens per session scan A 9f4ed0f412cd
ccc-multi-backend is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,459 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to multi-backend, differing in 198 lines, and is treated as a copy.
Other commands, from other repositories
symfony-doctrine-relations
Guide for implementing Doctrine entity relationships (OneToMany, ManyToMany).
dev-supabase
Configure and use Supabase as a backend (Auth, Database, Storage, Realtime, Edge Functions).
saved-object
Generate a custom Saved Object type with registration, mappings, migrations, CRUD service, and management integration for a Kibana plugin.
dev-prisma
Command "dev-prisma" from christopherlouet/claude-base, covering agent dev-prisma (pointer), context, delegate to the vendor toolkit, prisma's preferred path (verify on their readme) and fallback — clone and copy.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.
implement-caching-strategy
Command "implement-caching-strategy" from qdhenry/Claude-Command-Suite, covering implement caching strategy and instructions.