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 agentmods add commands/kevinzai/commander/ccc-multi-repogit 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-repo)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-multi-repo"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-multi-repo.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 | $0.00014 | $0.01325 |
| Opus 5 | $0.00007 | $0.00662 |
| Sonnet 5 | $0.00003 | $0.00265 |
| Haiku 4.5 | $0.00001 | $0.00133 |
Grade A, and why
ccc-multi-repo 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.
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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Repo
Make coordinated changes across multiple repositories in a single Claude Code session. Perfect for API contract changes, shared library updates, and cross-service refactoring.
Usage
/multi-repo # Interactive setup
/multi-repo add ~/projects/other-repo # Add a repo to current session
/multi-repo status # Show all repos in session
Quick Start
From the CLI
# Primary repo + additional repos
cd ~/projects/api-server
claude --add-dir ~/projects/web-client --add-dir ~/projects/mobile-app
# Short form
claude -a ~/projects/web-client -a ~/projects/mobile-app
From Within a Session
/multi-repo add ~/projects/web-client
# Added ~/projects/web-client to session.
# You can now read, edit, and run commands in both repos.
/multi-repo add ~/projects/mobile-app
# Added ~/projects/mobile-app to session.
# 3 repos active: api-server, web-client, mobile-app
Check Status
/multi-repo status
Active repositories:
1. ~/projects/api-server (primary) branch: main clean
2. ~/projects/web-client (added) branch: main clean
3. ~/projects/mobile-app (added) branch: main clean
Common Workflows
API Contract Change
When you modify an API endpoint and need all clients to update:
I'm adding a `displayName` field to the User API response and
deprecating the `name` field.
Update all three repos:
1. api-server: schema, handler, validation, tests
2. web-client: types, API client, all components using `name`
3. mobile-app: types, API service, all screens using `name`
Create a feature branch in each repo. All repos must typecheck and pass tests.
Shared Type Library Update
When your shared types package gets a breaking change:
I'm updating @company/shared-types to v3.0.
Changes:
- UserId is now a branded type (not just string)
- Date fields use Temporal instead of Date
Update all consuming repos to work with the new types.
Run typecheck and tests in each repo.
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.
- today First seen · 229 lines · 14 tokens per session scan A 209eaba835f1
ccc-multi-repo is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 1,325 once invoked, about $0.0001 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 2026-09-04.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
review
Run a Codex code review of your working tree or a branch (read-only).
adv-codex
Send a prompt to Codex CLI and return the response.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
planning-triage
Quick-score an enhancement, bug, or feedback item using the impact-first triage framework. Creates an issue if approved.
add-hook
Add a new hook to .claude/settings.json. Quick operation, no full interview needed. Trigger phrases: "add hook", "auto-format on save", "run tests after edit", "lint on write", "run [command] after [tool]".