voice-session

A conversational command for discovering and recording the narrator's voice and a character's way of speaking in a long fiction project.

In plain words
What is it for?
It helps create or extend a voice document through a full authorial-voice session or a focused profile for a named character.
Why use it?
Writers may know that a manuscript sounds inconsistent without having a written description of the consciousness and voices they want to preserve.

Command

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/third-order-labs/longform-plugin/voice-session
Clone the repo
git clone --depth 1 https://github.com/third-order-labs/longform-plugin
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,959 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 $0.00021 $0.02959
Opus 5 $0.00010 $0.01479
Sonnet 5 $0.00004 $0.00592
Haiku 4.5 $0.00002 $0.00296

Measured yesterday against content hash 4c3030709350, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

voice-session 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 yesterday.

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-session.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voice-session — Capture Authorial Voice

Conversational voice capture for long-form fiction. Produces or extends docs/08-voice.md — the document that captures the narrator's consciousness and character voices.

This can happen at any point in the project. Some writers want to establish voice before chapter one. Others discover it through the first few chapters and capture it once it's emerged. Both are valid — the session adapts to where the project is.

Invocation

/voice-session                    # Full authorial consciousness session
/voice-session character "Elena"  # Character voice profile for a specific character

Skills Referenced

  • authorial-voice — theory of voice in long-form fiction, voice doc structure, anti-patterns

Modes

Mode 1: Full Session (Authorial Consciousness)

Produces the authorial consciousness layer — the narrator's worldview, attention filter, and stance toward events. This is the deep capture that shapes how every scene reads.

Mode 2: Character Voice

Shorter, focused on a specific POV character. Adds or updates a character voice profile in docs/08-voice.md.


Mode 1: Full Authorial Consciousness Session

Setup

Check if docs/08-voice.md already exists.

If it exists: Read it. It might have been created empty by /start-project, seeded with observations by /write-chapter, or populated by a previous voice session. Confirm with the user whether they want to revise, extend, or start fresh. If extending, note what's already captured and where the gaps are.

If it doesn't exist: That's fine — this session will create it.

If chapters have been drafted: Read the recent drafts before starting the conversation. The existing prose is voice data. You're not starting from zero — you're articulating what's already on the page. This changes the conversation: instead of asking "what kind of narrator do you want?" you can say "I'm noticing [pattern] in your chapters — is that intentional? Is that the narrator you want?"

Read the full file on GitHub · 229 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. yesterday First seen · 229 lines · 21 tokens per session scan A 4c3030709350

Subscribe to this mod's changes

voice-session is a command published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 2,959 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.