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-peersgit 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-peers)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-peers"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-peers.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 | $0.00012 | $0.02647 |
| Opus 5 | $0.00006 | $0.01324 |
| Sonnet 5 | $0.00002 | $0.00529 |
| Haiku 4.5 | $0.00001 | $0.00265 |
Grade A, and why
ccc-peers 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/peers — Claude Peers Communication Hub
You are the Claude Peers communication interface. When the user invokes /peers, parse the subcommand and execute the appropriate action using the Claude Peers MCP tools. If no subcommand is given, show active peers with their summaries.
Routing
/peersor/peers list→ Calllist_peers, show active peers with summaries/peers send <id> <message>→ Send message to specific peer/peers status→ Show all peers with their current work status and pending messages/peers broadcast <message>→ Send message to all active peers/peers summary <text>→ Update your own summary/peers check→ Check for incoming messages/peers help→ Quick reference card
/peers or /peers list — List Active Peers
Discover all active Claude Code instances visible from this machine.
Steps:
-
Call
list_peerswith scoperepo(default — peers in the same git repository) -
If no peers found with
reposcope, automatically trydirectorythenmachinescope. Report which scope returned results. -
Display results:
ACTIVE PEERS (scope: repo)
===========================
ID: abc123def456
Summary: "Backend peer: implementing JWT auth endpoints"
CWD: ~/project/src/api
---
ID: xyz789ghi012
Summary: "Frontend peer: building login page components"
CWD: ~/project/src/components
---
ID: mno345pqr678
Summary: "Test writer: writing auth integration tests"
CWD: ~/project/tests
---
Total: 3 peers found
Actions:
/peers send <id> <message> — message a specific peer
/peers broadcast <message> — message all peers
/peers status — full dashboard with messages
- If no peers found at any scope:
NO PEERS FOUND
===============
No other Claude Code instances detected on this machine.
To create peers:
- Open a new terminal tab and run: claude
- Or use: /spawn quick <task>
- Or use: /spawn team <n>
Peers auto-discover each other via the Claude Peers MCP server.
No configuration needed.
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 · 358 lines · 12 tokens per session scan A f2aad2ff9c9f
ccc-peers is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 2,647 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]".