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.
npx agentmods add skills/third-order-labs/longform-plugin/authorial-voicenpx skills add third-order-labs/longform-plugin --skill authorial-voicegit clone --depth 1 https://github.com/third-order-labs/longform-pluginWrote 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.
[](https://agentmods.dev/skills/third-order-labs/longform-plugin/authorial-voice)<a href="https://agentmods.dev/skills/third-order-labs/longform-plugin/authorial-voice"><img src="https://agentmods.dev/badge/skills/third-order-labs/longform-plugin/authorial-voice.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00040 | $0.02340 |
| Opus 5 | $0.00020 | $0.01170 |
| Sonnet 5 | $0.00008 | $0.00468 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
authorial-voice 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authorial Voice
Voice in long-form fiction is the deeper problem beneath coherence. Continuity tracking ensures chapter 40 doesn't contradict chapter 2. Voice ensures the novel reads like it was written by one consciousness with a consistent worldview across 300 pages. This skill covers capturing that consciousness and maintaining it at scale.
Voice vs. Style
Style guide = surface. Prose register, sentence length, POV rules, dialogue formatting. You can follow a style guide and produce competent generic prose. Two different writers can follow the same style guide and produce completely different novels.
Authorial voice = the perceptual filter underneath. What the narrator pays attention to, what they skip, what they believe about the world. You can't follow a checklist for this — it has to be consistent across 300 pages because it comes from a consistent consciousness.
The style guide says HOW to write. The voice doc says WHO is writing.
Hemingway didn't write short declarative sentences because of a style guide. He wrote that way because of who he was — his worldview produced the style. The authorial consciousness layer captures the who, not just the how.
The Authorial Consciousness Layer
What the voice doc captures — not a style spec, but a portrait of the mind behind the prose:
Attention filter
What does this narrator notice? Physical spaces? Social dynamics? Interior states? The mundane? Power structures? The body?
A narrator who lingers on landscape writes differently from one who lingers on power dynamics — and this colors every scene, not just the ones "about" that thing. The attention filter determines which details make it onto the page and which get passed over. It's the most pervasive element of voice because it operates in every paragraph.
Beliefs about the world
Not the theme of the novel — the narrator's operating assumptions. Do people change? Are institutions redeemable? Is violence ever justified? Is love sufficient? Does effort correlate with outcome? Is the universe indifferent or responsive?
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.
- 5d ago First seen · 151 lines · 40 tokens per session scan A f42e89767ad1
authorial-voice is a skill published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 2,340 once invoked, about $0.0002 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.
Other skills, from other repositories
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…
miniapp-dev
Develops, maintains, and generates OpenBitFun MiniApps (Zero-Dialect Runtime). Use when (1) working on miniapp framework code under src/crates/assembly/core/src/miniapp/ or src/web-ui/src/app/scenes/miniapps/; or (2) generating / creating / designing a NEW MiniApp for the user — including any request like "做一个小应用 / 生成…
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…
pr-review-canvas
Create a OpenBitFun Canvas for reviewing a pull request, branch diff, or change set with Cursor-style diff cards, review maps, risk callouts, and focused reviewer flow. Use when the user asks for a PR review canvas, diff walkthrough, change-set overview, or visual review summary.