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 commands/third-order-labs/longform-plugin/plan-chaptergit clone --depth 1 https://github.com/third-order-labs/longform-pluginWhat 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 | $0.00024 | $0.01728 |
| Opus 5 | $0.00012 | $0.00864 |
| Sonnet 5 | $0.00005 | $0.00346 |
| Haiku 4.5 | $0.00002 | $0.00173 |
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.
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 awarenessnarrative-craft— thread health, foreshadowing awarenessscene-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 contradictionsdocs/03-characters.md— who's in the story, arc directionsdocs/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 danglingdocs/04-outline.md— what the structural plan says should happen around this chapterdocs/13-threads.md— which threads are active, which need oxygendocs/19-foreshadowing-checklist.md— any seeds that need planting in this windowdocs/25-style-guide.md— prose targets and constraintsdocs/08-voice.md— authorial consciousness and POV character profilesdocs/05-glossary.md— established names and terms- Any other project-specific reference docs (world, timeline, relationships, etc.)
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.
- yesterday First seen · 170 lines · 24 tokens per session scan A 43927069063b
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.
Other commands, from other repositories
onboard-interactive
Interactive customer onboarding with Step 0 independent verification (dialog-based, 17 stagegates).
monitor
AML transaction monitoring and suspicious activity reporting.
skip_sample
Skip sample-first mode for this request — fetch/enrich at full scale without a 5-entity preview.
dev-flow
从 PRD 到交付的完整 8 步研发流程.
axonflow-status
Show your AxonFlow tenantid (needed for Stripe Pro checkout), endpoint, tier (Free vs Pro), and Pro license expiry date.
unit-economics
Unit economics analysis — CAC/LTV estimation, churn inference, gross margin per unit.