send

send is a command for Claude Code from Kenmege/codex-claude-companion. It costs 14 tokens per session (210 once invoked), scanned A, original, Apache-2.0.

A command for sending a message to a running Claude review worker, the process currently performing a review. It attaches the message to a specific review job.

In plain words
What is it for?
Use it to send focused guidance to an ongoing review, optionally waiting for Claude to acknowledge that the message was received.
Why use it?
It lets you steer an active review with additional instructions while preserving the job’s message order and stored state.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions Codex.

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/kenmege/codex-claude-companion/send
Clone the repo
git clone --depth 1 https://github.com/Kenmege/codex-claude-companion

Made for: Claude Code.

Wrote 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.

agentmods badge for send

README.md
[![agentmods](https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/send.svg)](https://agentmods.dev/commands/kenmege/codex-claude-companion/send)
Your own site
<a href="https://agentmods.dev/commands/kenmege/codex-claude-companion/send"><img src="https://agentmods.dev/badge/commands/kenmege/codex-claude-companion/send.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 210 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 5.1 $0.00014 $0.00210
Opus 5 $0.00007 $0.00105
Sonnet 5 $0.00003 $0.00042
Haiku 4.5 $0.00001 $0.00021

Measured 5d ago against content hash 93db80077263, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

send 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 5d 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.

commands/send.md · 22 lines

What it actually says

/claude-review:send

Confirm the target job and send exactly the user's intended text:

codex-claude send <ccb_job-id> --message "<text>"

Use --wait only when the caller wants to wait for acknowledgement. Messages are ordered and deduplicated in durable state, but they can change worker behavior; do not send secrets, credentials, or a broader authorization than the user gave.

Live same-session steering exists only until the authoritative Claude result is observed. At that boundary the managed input stream closes so verification and delivery can start. Without --wait, success means only that the message was durably queued. With --wait, success requires Claude to replay-acknowledge it; a terminal-result race can therefore leave a queued message unacknowledged. After the job is terminal, start or resume follow-up work instead of treating send as a continuation channel.

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. 5d ago First seen · 22 lines · 14 tokens per session scan A 93db80077263

Subscribe to this mod's changes

send is a command published in the GitHub repository Kenmege/codex-claude-companion (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 210 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 2026-08-31.