A voice command that stops the current Cadence Code audio and captures one new spoken instruction. Cadence Code is a local voice interface for coding-agent conversations.

Use it after pressing Escape when you want to add guidance, change the task, resume with a spoken instruction, or stop the voice conversation.

It lets you interrupt an active spoken turn and redirect the task without starting the voice session again or typing the new instruction.

jump-in — Command for coding agents by michael-L-i: A voice command that stops the current Cadence 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/michael-l-i/cadence-code/jump-in

Clone the repo

git clone --depth 1 https://github.com/michael-L-i/cadence-code

Or install cadence-code, the plugin that ships this one along with the rest of its 4 skills, 4 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/michael-l-i/cadence-code/jump-in.svg)](https://agentmods.dev/commands/michael-l-i/cadence-code/jump-in)

Your own site

<a href="https://agentmods.dev/commands/michael-l-i/cadence-code/jump-in"><img src="https://agentmods.dev/badge/commands/michael-l-i/cadence-code/jump-in.svg" alt="Measured on agentmods" height="20"></a>

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 338 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.

Model	Per session	Once invoked
Fable 5	$0.00006	$0.00338
Opus 5	$0.00003	$0.00169
Sonnet 5	$0.00001	$0.00068
Haiku 4.5	$0.00001	$0.00034

Measured 4d ago against content hash 10b87fbc3425, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jump-in 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.

commands/jump-in.md · 28 lines

What it actually says

Interrupt the current Cadence Code audio and collect one fresh spoken instruction with mcp__cadence-code__voice_interrupt. This command is intended to be invoked after the user presses Escape to stop the current Claude Code turn.

Call mcp__cadence-code__voice_interrupt immediately. Do not call voice_start, voice_speak, or ordinary voice_listen first.
If it returns ok: false, show the error. If Cadence Code is inactive, tell the user to run /cadence-code:start-talking; do not start it implicitly.
Treat every non-empty transcript as added guidance for the interrupted task, including one returned with end_reason: "timeout". Continue from current conversation and repository state without asking whether to resume. If the guidance redirects or replaces the work, follow it normally.
If no speech is detected, leave the interrupted task stopped, report that no guidance was captured, and do not listen again automatically.
On end_reason: "device_error", show the microphone problem and leave Cadence Code active so the user can retry or run /cadence-code:wrap-up.
If the transcript clearly asks to end Cadence Code entirely, call mcp__cadence-code__voice_stop and do not resume the task.

After accepting the guidance, continue the normal Cadence Code workflow: work silently, then provide the concise spoken result and detailed written result before listening for the next turn.

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.

4d ago First seen · 28 lines · 6 tokens per session scan A 10b87fbc3425

Subscribe to this mod's changes

jump-in is a command published in the GitHub repository michael-L-i/cadence-code (2 stars, last pushed 4d ago), licensed MIT. It adds 6 tokens to every session and 338 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.

Apple Silicon claude-code claude-code-plugin mlx speech-to-text text-to-speech

jump-in

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

summary-say

tts-init

tts-mute

tts-start

tts-status

tts-stop