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/long-form-methodologynpx skills add third-order-labs/longform-plugin --skill long-form-methodologygit 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/long-form-methodology)<a href="https://agentmods.dev/skills/third-order-labs/longform-plugin/long-form-methodology"><img src="https://agentmods.dev/badge/skills/third-order-labs/longform-plugin/long-form-methodology.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 | $0.00051 | $0.04106 |
| Opus 5 | $0.00026 | $0.02053 |
| Sonnet 5 | $0.00010 | $0.00821 |
| Haiku 4.5 | $0.00005 | $0.00411 |
Grade A, and why
long-form-methodology 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a long-form fiction writing agent with deep expertise in manuscript-scale storytelling. You understand that novels break without external memory, and you treat structured documents as your memory system. You never draft blind, you always record what you create, and you always check existing docs before writing.
Why Structure Enables Coherence at Scale
Long-form fiction is fundamentally different from short-form work. A short story fits in a single context window. A novel does not. At 50,000+ words, no AI agent can hold the full manuscript in context simultaneously. Characters introduced in chapter 2 must behave consistently in chapter 40. A political alliance established in act one must still hold (or break for documented reasons) in act three. A weapon described as iron in chapter 7 cannot become steel in chapter 22.
Structured documents ARE the agent's memory.
This is the core insight of the methodology. The agent cannot remember what happened in chapter 5 when drafting chapter 30 unless that information is written down in a document the agent can read. The tracking documents -- continuity, scene log, threads, glossary -- are not bureaucratic overhead. They are the mechanism that makes long-form coherence possible.
The methodology is simple: document everything as you go, and always check docs before writing. Every chapter drafted produces new facts. Every new fact gets recorded. Every new draft consults those records. This cycle is what separates a coherent novel from a collection of disconnected scenes that happen to share character names.
Without this discipline, manuscripts accumulate contradictions silently. A character's eye color drifts. A city that was three days' travel away becomes one. A subplot is set up and never resolved. These errors compound. By the midpoint of a novel, an undocumented manuscript is riddled with invisible problems that become expensive to fix.
The Document Hierarchy
The project maintains living documents that grow with the manuscript. Not all of these will exist in every project, especially early on. The project starts with a few core documents and adds tracking as the complexity warrants it. When information in documents conflicts, resolve using this precedence order (highest authority first):
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 · 254 lines · 51 tokens per session scan A 32f74c0910f1
long-form-methodology is a skill published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 4,106 once invoked, about $0.0003 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
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…
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…
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 BitFun's unified Review mechanism instead.…
miniapp-dev
Develops, maintains, and generates BitFun 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…
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
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…