cb-usage

A command that reports Code Brain activity, including Claude and Codex token use, hook and MCP activity, and blocked tool calls. Hooks are automatic project actions, while MCP is a way for an agent to call connected tools.

In plain words
What is it for?
Use it to print session counts, input and output tokens, cached tokens, injected context, hook and MCP counts, and blocked PreToolUse calls.
Why use it?
It gives a fixed, compact usage report without manually inspecting separate logs or tool records.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/ezbuilder/code-brain/cb-usage
Clone the repo
git clone --depth 1 https://github.com/ezBuilder/code-brain

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00496
Opus 5 $0.00014 $0.00248
Sonnet 5 $0.00006 $0.00099
Haiku 4.5 $0.00003 $0.00050

Measured 2d ago against content hash 54ce36974aa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cb-usage 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 2d 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.

.claude/commands/cb-usage.md · 30 lines

What it actually says

.ai/bin/ai obs usage --json 실행. 정확히 아래 형식만 평문 출력. 표·박스·이모지·코드블록·헤더·해설 모두 금지.

JSON 경로:

  • actual_token_usage.{claude,codex}.{source, sessions_matched, tokens.{input_tokens, output_tokens, cache_read_input_tokens, cached_input_tokens}}
  • measured_code_brain_effect.{additional_context_bytes, mcp_response_bytes, hook_events, mcp_requests, pretooluse_blocks, hook_breakdown, mcp_breakdown}

출력 (천 단위 콤마):

코드브레인 활동
- Claude: {claude.sessions_matched}세션 · 입력 {input_tokens} / 출력 {output_tokens} / cache_read {cache_read_input_tokens}
- Codex: {codex.sessions_matched}세션 · 입력 {input_tokens} / 출력 {output_tokens} / cached {cached_input_tokens}
- 주입: {additional_context_bytes} B (hook), {mcp_response_bytes} B (mcp 응답)
- hook {hook_events}회 [{hook_breakdown 요약: 예 "Session 18 / Prompt 35 / PreTool 12(blocked 8)"}]
- mcp {mcp_requests}회 [{mcp_breakdown 요약: 예 "code_query 4 / sandbox_execute 3 / obs_health_summary 5"}]
- ★ PreToolUse 차단 {pretooluse_blocks}회 (Code Brain이 grep 덤프 방지한 횟수)

규칙:

  • claude.source != "claude_transcript" 시 첫 줄을 - Claude: (transcript 없음 — source: <source>).
  • codex.source != "codex_transcript" 시 둘째 줄 동일 패턴.
  • hook_breakdown 요약: 카운트 desc 정렬, 상위 4개만, "이름 N(blocked X)" 형식.
  • mcp_breakdown 요약: 동일.
  • "saved/savings/절약" 단어 사용 금지.
  • 위 7줄 외 한 글자도 추가 금지.
Changes

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.

  1. 2d ago First seen · 30 lines · 28 tokens per session scan A 54ce36974aa2

Subscribe to this mod's changes

cb-usage is a command published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 28 tokens to every session and 496 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 2026-08-30.