agentmods.dev

voice-interview

A guided interview that records how you write in a voice profile file.

In plain words
What is it for?
Use it to set up or redo a Founder OS voice profile for posts, client updates, proposals, emails, standard procedures, and reused content.
Why use it?
It avoids making writing tools guess your tone and style from scratch. The saved profile can guide later writing tasks.

Command for Claude Code

5 19d ago A scan 82 tokens original MIT
View the source file ARCASSystems/FounderOS
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/arcassystems/founderos/voice-interview
Clone the repo
git clone --depth 1 https://github.com/ARCASSystems/FounderOS

Made for: Claude Code.

Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 600 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 $0.00082 $0.00600
Opus 5 $0.00041 $0.00300
Sonnet 5 $0.00016 $0.00120
Haiku 4.5 $0.00008 $0.00060

Measured 2d ago against content hash 81e07d043103, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

voice-interview 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 2d 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.

.claude/commands/voice-interview.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Founder OS voice interview

Entry point for the voice interview. Triggers the voice-interview skill, which captures the user's writing voice and writes it to core/voice-profile.yml.

Procedure (in order)

  1. Check whether core/identity.md exists at the repo root.

  2. If core/identity.md does NOT exist, reply: Founder OS not set up here yet. Say "set up Founder OS" first. and stop. The voice interview depends on identity being filled.

  3. Check whether core/voice-profile.yml exists.

    • If it does NOT exist, copy the template from templates/voice-profile.yml.template to core/voice-profile.yml (placeholders intact) before invoking the skill, so the skill can fill it in place.

    • If it exists, scan its content for placeholder markers: [CHOOSE:, [YOUR , [example:, [NOT SET]. If ALL voice fields still contain these markers (no field has been replaced with a real value), the profile is placeholder-only - proceed directly into the interview without asking for confirmation.

    • If at least one field has been filled with a real value (no longer a placeholder), ask the founder, as a single message:

      Voice profile already filled. Re-run the interview and overwrite? (yes / no)

      Wait for the reply. If the reply is a clear no, reply: Voice interview dismissed. Existing profile left untouched. and stop. If the reply is a clear yes, proceed.

  4. Read the voice-interview skill at skills/voice-interview/SKILL.md and execute it end to end. The skill owns the interview flow: welcome, samples, shaping questions, confirmation, write. Follow its phases IN ORDER. Do not shortcut.

Rules

  • This command is a thin trigger. All logic lives in the skill. Do not duplicate interview steps here.
  • If the skill file is missing, reply: Voice interview skill not found at skills/voice-interview/SKILL.md. Restarting Claude Code fixes this most of the time, because it reloads what is installed. If it happens again after a restart, say "update Founder OS". and stop.
  • No em dashes or en dashes. Hyphens only with spaces.
  • Never overwrite an existing populated profile without the explicit re-run confirmation above.

Read the full file on GitHub · 36 lines

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. 2d ago First seen · 36 lines · 82 tokens per session scan A 81e07d043103

Subscribe to this mod's changes

voice-interview is a command published in the GitHub repository ARCASSystems/FounderOS (5 stars, last pushed 19d ago), licensed MIT. It adds 82 tokens to every session and 600 once invoked, about $0.0004 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.

Writing and docsai-agentsclaude-codefounder-osllms-txtmarkdownoperating-system
Related

Other commands, from other repositories

wiki-init

Initialize a new LLM Wiki in the current directory. Creates the full directory structure, config, and template files.

zosmaai/pi-llm-wiki · 23 tokens

check-invariants

Runs only the tree CRDT invariant test battery in outl-core. Faster than /check, focused on what can break sync.

outlmd/outl · 26 tokens

prd-review

Review the active PRD with Codex and stream normalized findings to JSONL.

assafkip/kipi-system · 15 tokens

claude-cmd-status

A Claude Code slash command. OpenCode does not read Claude commands.

crystian/skill-map · 14 tokens

ingest-l1

L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…

Gixsy95/abap_wiki · 86 tokens

web-search

Search fetched web-source Markdown by regex and pull surrounding context for the best hits. Optionally restrict to one source alias.

raintree-technology/docpull · 24 tokens