cb-exec

A command that runs a shell command in Code Brain’s sandbox and summarizes the result. A sandbox is an isolated environment for running commands with controlled access.

In plain words
What is it for?
Use it to run commands such as grep or find, see the first and last output lines, and fetch selected lines later by execution ID.
Why use it?
It keeps long command output from filling the conversation while preserving the full output in a cache for later retrieval.

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-exec
Clone the repo
git clone --depth 1 https://github.com/ezBuilder/code-brain

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 283 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 $0.00023 $0.00283
Opus 5 $0.00012 $0.00142
Sonnet 5 $0.00005 $0.00057
Haiku 4.5 $0.00002 $0.00028

Measured yesterday against content hash 85439f0c828d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cb-exec 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 yesterday.

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-exec.md · 25 lines

What it actually says

$ARGUMENTS가 비었으면 사용법: /cb-exec -- <command> [args...] 한 줄 출력 후 stop.

.ai/bin/ai exec run --json -- $ARGUMENTS 실행 후 정확히 다음 형식으로 출력. 표·박스·이모지·코드블록 금지.

sandbox 실행: exec_id={exec_id} exit={exit_code}
- 출력: {total_lines}줄 / {total_bytes} B (cache: .ai/cache/sandbox/{exec_id}.txt)
- 첫 줄들:
{first_lines.join("\n")}
- 마지막 줄들 (있으면):
{last_lines.join("\n")}

추가 줄 조회: .ai/bin/ai exec fetch --exec-id {exec_id} --line-start 1 --line-end 200 --json 또는 --grep <패턴>.

규칙:

  • 자동 fetch 금지 — 사용자가 exec_id로 명시 요청 시에만 추가 실행.
  • 본문 가공 금지. JSON에서 그대로.
  • 위 형식 외 한 글자도 추가하지 않는다.
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. yesterday First seen · 25 lines · 23 tokens per session scan A 85439f0c828d

Subscribe to this mod's changes

cb-exec is a command published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 283 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.