agentmods.dev

voice-resume

voice-resume is a command for Claude Code from zircote/human-voice. It costs 12 tokens per session (435 once invoked), scanned A, original, MIT.

A command for continuing a paused voice interview session. It lists resumable sessions, restores one, and hands the conversation back to the interview process.

In plain words
What is it for?
Use it to find paused or active sessions, choose one, review its saved state, and continue asking the remaining questions.
Why use it?
It lets an unfinished spoken requirements interview continue without losing its previous answers or progress.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the human-voice plugin — 2 skills, 12 commands, 3 agents, 1 hook shipped together

not rated 10repo 1mo ago A scan 12 tokens original MIT

Good fit Use it to find paused or active sessions, choose one, review its saved state, and continue asking the remaining questions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/zircote/human-voice/voice-resume
View source ↗ zircote/human-voice
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.

Clone the repo
git clone --depth 1 https://github.com/zircote/human-voice

Made for: Claude Code.

Or install human-voice, the plugin that ships this one along with the rest of its 2 skills, 12 commands, 3 agents, 1 hook.

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 voice-resume

README.md
[![agentmods](https://agentmods.dev/badge/commands/zircote/human-voice/voice-resume/github.svg)](https://agentmods.dev/commands/zircote/human-voice/voice-resume)
Your own site
<a href="https://agentmods.dev/commands/zircote/human-voice/voice-resume"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-resume/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for voice-resume

Your own site · 80×15
<a href="https://agentmods.dev/commands/zircote/human-voice/voice-resume"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00012 $0.00435
Opus 5 $0.00006 $0.00217
Sonnet 5 $0.00002 $0.00087
Haiku 4.5 $0.00001 $0.00044

Measured 8d ago against content hash be4a6107b96d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

voice-resume 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 8d 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/voice-resume.md · 40 lines

What it actually says

/resume — Resume a Paused Interview Session

Resume a previously paused voice interview session.

Procedure

  1. List sessions: Run bin/voice-session list to get all sessions as JSON.

  2. Filter resumable: Show sessions with state of paused or in_progress. If a session ID was provided as an argument, use that directly. If no resumable sessions exist, suggest /voice-interview.

  3. Present choices: If multiple resumable sessions, display a table and use AskUserQuestion:

    #  Session ID     State         Module  Questions  Updated
1  a1b2c3d4-...   paused        M03     18/~70     2026-04-01
2  e5f6g7h8-...   in_progress   M07     42/~70     2026-03-28

  4. Resume session: Run bin/voice-session resume {session_id} to restore state.

  5. Launch conductor: Spawn the interview-conductor agent with this prompt:

    You are resuming a paused voice elicitation interview.

    Session ID: {session_id} Session directory: {session_dir} Project root: {project_root}

    Load state.json, recap progress conversationally to the user, then run the FULL interview loop. Use bin/voice-sequencer next-question to get each question, present it via AskUserQuestion, record the response, update state, and loop. Do NOT exit after a single question — continue until the interview is complete or the user pauses again.

Output

Confirm which session was resumed, show progress, then present the next question.

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. 8d ago First seen · 40 lines · 12 tokens per session scan A be4a6107b96d

Subscribe to this mod's changes

voice-resume is a command published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 435 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.

Claude Codeai-detectionclaude-code-plugincontent-qualitymarkdown
Related

Other commands, from other repositories

graph

Extract prerequisite concept graph from converted course materials and write course-index/concept-graph.md.

OPTIMETA/PAIDEIA · 18 tokens

alt

Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.

OPTIMETA/PAIDEIA · 44 tokens

quiz

Generate N practice problems on a topic. Saves problem MD + hidden answer MD. User solves on paper, uploads answer PDF, then runs /grade. First arg weakmap → auto-load latest weakmap report and target its top weaknesses.

OPTIMETA/PAIDEIA · 49 tokens

weakmap

Priority-ranked weakness report. No arg → fresh report from latest errors per pattern. With concept arg → patch latest report by adding the user-declared weakness, save as new timestamped file.

OPTIMETA/PAIDEIA · 38 tokens

derive

Save a clean reference derivation of a target equation or theorem to derivations/. Draws from course materials (textbook, lecture notes) rather than testing the user.

OPTIMETA/PAIDEIA · 34 tokens

mock

Generate a mock exam matched to the course's structure (inferred from course-index). Saves problem MD + hidden solution MD. User solves on paper, uploads PDF, runs /grade.

OPTIMETA/PAIDEIA · 37 tokens