recap

recap is a command for coding agents from punt-labs/vox. It costs 7 tokens per session (199 once invoked), scanned A, original, MIT.

A command that turns the previous response into a short spoken summary.

In plain words
What is it for?
Use `/vox:recap` after a task or explanation to hear and see a factual summary of the last response.
Why use it?
It saves you from rereading the full response when you only need the main changes, actions, or findings.

Command

Part of the vox-dev plugin — 10 commands, 9 hooks shipped together

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/punt-labs/vox/recap
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

Or install vox-dev, the plugin that ships this one along with the rest of its 10 commands, 9 hooks.

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 recap

README.md
[![agentmods](https://agentmods.dev/badge/commands/punt-labs/vox/recap.svg)](https://agentmods.dev/commands/punt-labs/vox/recap)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/vox/recap"><img src="https://agentmods.dev/badge/commands/punt-labs/vox/recap.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 199 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 $0.00007 $0.00199
Opus 5 $0.00003 $0.00100
Sonnet 5 $0.00001 $0.00040
Haiku 4.5 $0.00001 $0.00020

Measured 4d ago against content hash 85d78643dffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recap 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 4d 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.

plugin/commands/recap.md · 25 lines

What it actually says

/vox:recap command

Speak a brief summary of the last response.

Usage

/vox:recap

Implementation

  1. Look at your most recent response (before this command) — the one the user wants summarized.
  2. Extract the 2-3 most important points: what changed, what was done, any key findings.
  3. Write the summary as clear, concise spoken text (30 seconds when spoken, roughly 60-80 words).
  4. Call the unmute MCP tool with:
    • text: your summary
    • ephemeral: true
  5. Show the summary text in the conversation as well (voice supplements text, never replaces it).

Keep the summary factual. No filler words. No "Here's a summary of..." preamble — just the content.

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. 4d ago First seen · 25 lines · 7 tokens per session scan A 85d78643dffa

Subscribe to this mod's changes

recap is a command published in the GitHub repository punt-labs/vox (3 stars, last pushed 4d ago), licensed MIT. It adds 7 tokens to every session and 199 once invoked, about $0.0000 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.