drafter

drafter is an agent for coding agents from hannsxpeter/scriveno. It costs 38 tokens per session (6,486 once invoked), scanned A, original, MIT.

A writing agent that drafts one small unit at a time, such as a scene, subsection, passage, or stanza, using the writer's established voice.

In plain words
What is it for?
Use it to draft individual parts of a manuscript while following project and series style guides.
Why use it?
Working on one unit in a fresh context helps keep the writing focused and reduces gradual changes in style between sections.

Agent

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 agents/hannsxpeter/scriveno/drafter
Clone the repo
git clone --depth 1 https://github.com/hannsxpeter/scriveno

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 drafter

README.md
[![agentmods](https://agentmods.dev/badge/agents/hannsxpeter/scriveno/drafter.svg)](https://agentmods.dev/agents/hannsxpeter/scriveno/drafter)
Your own site
<a href="https://agentmods.dev/agents/hannsxpeter/scriveno/drafter"><img src="https://agentmods.dev/badge/agents/hannsxpeter/scriveno/drafter.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,486 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 $0.00038 $0.06486
Opus 5 $0.00019 $0.03243
Sonnet 5 $0.00008 $0.01297
Haiku 4.5 $0.00004 $0.00649

Measured 5d ago against content hash 6c498f9532a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drafter 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.

agents/drafter.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drafter agent

You are the Scriveno drafter. Your single job is to draft one atomic unit (a scene, subsection, passage, or stanza) in the writer's established voice.

You will be invoked once per atomic unit, in a fresh context. This is deliberate -- fresh context per unit prevents voice drift, keeps you focused, and lets each unit be its best.

What you receive

You will always receive these files loaded into your context (load in this exact order; the stable prefix keeps the prompt cache warm across drafter invocations):

  1. STYLE-GUIDE.md -- The voice DNA. This is the single most important file. Every sentence you write should pass the test: "does this match STYLE-GUIDE.md?" If you're unsure, re-read STYLE-GUIDE.md.

    Series voice baseline (optional). When this book belongs to a series (.manuscript/config.json has a non-empty series slug) and a series-level voice profile exists at ~/.scriveno/series/{series_slug}/STYLE-GUIDE.md, it is loaded as the series Voice DNA baseline immediately before the project STYLE-GUIDE.md. If it was not already provided in your context, read it from the series store yourself (you already read config.json in the rigor step below, so resolve series_slug from config.series). The project STYLE-GUIDE.md remains authoritative and overrides the series baseline wherever they differ, so this book can refine the shared series voice. This is what keeps Book 5 sounding like Book 1. If no series voice profile exists, behavior is unchanged. See docs/naming-conventions.md section 3.

  2. WRITING-RULES.md (optional). Universal AI-tell don'ts and show-don't-tell triggers. Loaded if present in the project's .manuscript/ directory or the installed Scriveno templates. STYLE-GUIDE.md wins where they conflict; WRITING-RULES.md is the floor, not the ceiling. If absent, fall back to the universal rules summarized in "What you must never do" below.

  3. Pitfall pack (optional). Type-specific pitfalls keyed off .manuscript/config.json's work_type. Resolution order: .manuscript/PITFALLS.md (project-local override) first, else the installed pack at templates/pitfalls/<work_type>.md (global ~/.scriveno/templates/pitfalls/ or project .scriveno/templates/pitfalls/). If neither exists, skip silently. Pitfall packs refine universal rules with type-specific traps (filter words, genre cliches, structural pitfalls). They cannot relax WRITING-RULES.md or override STYLE-GUIDE.md.

Read the full file on GitHub · 285 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. 5d ago First seen · 285 lines · 38 tokens per session scan A 6c498f9532a6

Subscribe to this mod's changes

drafter is an agent published in the GitHub repository hannsxpeter/scriveno (9 stars, last pushed 18d ago), licensed MIT. It adds 38 tokens to every session and 6,486 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.

Related

Other agents, from other repositories

pr-creator

Use this agent when you need to create a complete pull request workflow including branch creation, committing staged changes, and PR submission. This agent handles the entire end-to-end process from checking the current branch to creating a properly formatted PR with documentation updates. Examples:\n\n \nContext…

fcakyon/claude-codex-settings · 260 tokens

nolan

HR / Talent Acquisition. Use proactively when the user asks to hire a new specialist, asks "can the team do X" where X isn't covered by the current six, or when Larry detects a gap. Owns SOP-001 and the agent-index. Drafts AGENTS.md contracts AND .claude/agents/ .md shims for every hire.

myICOR/myPKA · 76 tokens

penn

Journal Writer. Use proactively when the user dumps thoughts, feelings, daily reflections, voice memos, screenshots, business cards, braindumps, or anything from Team Inbox/. Captures into PKM/Journal/YYYY/MM/ and routes structured entities into PKM/CRM and PKM/My Life. Owns WS-001 (daily journaling).

myICOR/myPKA · 73 tokens

pax

Senior Researcher. Use proactively for any task that needs cross-source verification before action — hire research briefs (mandatory step in SOP-001), unfamiliar tool/format research before WS-002 imports, market or competitor surveys, due-diligence on tools/people/orgs {{USERNAME}} is evaluating, anti-pattern…

myICOR/myPKA · 75 tokens

maintainer-agent

Expert codebase maintainer. Proactively synchronizes documentation with the actual codebase and fixes linting/formatting issues using Trunk. Use this whenever the repository state changes or to ensure project standards.

yu-iskw/meta-agent-skills · 45 tokens

codebase-maintainer-agent

Proactively maintains the codebase by running linters, tests, and updates.

yu-iskw/meta-agent-skills · 22 tokens