plan-chapter

A command for planning a fiction chapter before writing its draft.

In plain words
What is it for?
Use it to choose a chapter, review earlier scenes and story facts, discuss its direction, and create an outline for drafting.
Why use it?
It turns the available project context into an outline while adjusting the amount of planning to the project's current level of detail.

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/plan-chapter
Clone the repo
git clone --depth 1 https://github.com/third-order-labs/longform-plugin
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,728 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 $0.00024 $0.01728
Opus 5 $0.00012 $0.00864
Sonnet 5 $0.00005 $0.00346
Haiku 4.5 $0.00002 $0.00173

Measured yesterday against content hash 43927069063b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-chapter 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/plan-chapter.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/plan-chapter — Pre-Draft Chapter Planning

Plan a chapter before drafting. Load whatever context the project currently has, discuss direction with the user, and produce an outline spec. The depth of the outline scales with the project — a chapter 2 outline with minimal tracking docs looks different from a chapter 20 outline with a full suite of living documents.

Invocation

/plan-chapter
/plan-chapter next
/plan-chapter 12
/plan-chapter "The Crossing"

Skills Referenced

  • long-form-methodology — workflow loop (plan phase)
  • continuity-management — scene log review, canon awareness
  • narrative-craft — thread health, foreshadowing awareness
  • scene-craft — lived-in targets, texture planning

Workflow

Step 1: Identify the Chapter

Determine which chapter to plan:

  • If the user specifies a chapter number or title, use that
  • If "next" or no argument, determine the next unplanned chapter by checking existing outlines and drafts
  • If a scene log exists, check it for the last completed chapter
  • Confirm with the user: "Planning chapter [Y] — correct?"

Determine the book/volume (check which outlines/book-X/ and draft/book-X/ directories exist and contain work).

Step 2: Load What Exists

Read whatever context documents the project currently has. Not all of these will exist — use what's there.

Always exists:

  • docs/07-continuity.md — current canon; the outline must not set up contradictions
  • docs/03-characters.md — who's in the story, arc directions
  • docs/00-pitch.md — what the story is about

Read if present:

  • docs/06-scene-log.md — last 2-3 entries for immediate context: where are we, what just happened, what's dangling
  • docs/04-outline.md — what the structural plan says should happen around this chapter
  • docs/13-threads.md — which threads are active, which need oxygen
  • docs/19-foreshadowing-checklist.md — any seeds that need planting in this window
  • docs/25-style-guide.md — prose targets and constraints
  • docs/08-voice.md — authorial consciousness and POV character profiles
  • docs/05-glossary.md — established names and terms
  • Any other project-specific reference docs (world, timeline, relationships, etc.)

Read the full file on GitHub · 170 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 · 170 lines · 24 tokens per session scan A 43927069063b

Subscribe to this mod's changes

plan-chapter is a command published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,728 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.