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/write-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 | $0.00022 | $0.02759 |
| Opus 5 | $0.00011 | $0.01380 |
| Sonnet 5 | $0.00004 | $0.00552 |
| Haiku 4.5 | $0.00002 | $0.00276 |
Grade A, and why
write-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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/write-chapter — Draft a Chapter
The core workflow loop. Draft a chapter from its outline, then update whatever tracking documents exist and assess whether the project needs new ones. This is where manuscript and infrastructure grow together — the documents earn their existence through the work.
Invocation
/write-chapter
/write-chapter next
/write-chapter 12
/write-chapter "The Crossing"
Skills Referenced
long-form-methodology— workflow loop, document hierarchy, living document philosophycontinuity-management— scene log format, canon updates, glossary managementnarrative-craft— thread awareness, foreshadowing recognitionscene-craft— lived-in texture, dialogue craft, POV disciplineauthorial-voice— voice filtering and observation
Workflow
Step 1: Load the Chapter Outline
Locate the outline:
- If the user specifies a chapter, find the matching file in
outlines/book-X/ - If "next" or no argument, find the next unwritten outline (compare outlines to existing draft files)
- If no outline exists, inform the user: "No outline found for this chapter. Run
/plan-chapterfirst, or describe what you want this chapter to do and we'll work through it."
Read the full outline.
Step 2: Load What Exists
Check what documents the project currently has and read whatever is available. Not all of these will exist — especially in early chapters. Use what's there, note what's missing, don't fail.
Always exists (from /start-project):
docs/07-continuity.md— current canon; do not contradictdocs/03-characters.md— character profiles and arc directionsdocs/00-pitch.md— what the story is about
May exist — read if present:
docs/06-scene-log.md— recent entries for narrative context (last 2-3)docs/08-voice.md— authorial consciousness and character voice profilesdocs/05-glossary.md— correct names, terms, spellingsdocs/25-style-guide.md— prose register, POV, tense, length targetsdocs/13-threads.md— active thread trackingdocs/19-foreshadowing-checklist.md— seeds to plantdocs/02-world.md— world referencedocs/04-outline.md— series/book-level structural context- Any other project-specific tracking docs that have been created
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 · 181 lines · 22 tokens per session scan A 5cdc0f645815
write-chapter is a command published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 2,759 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.