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/narrative-craftnpx skills add third-order-labs/longform-plugin --skill narrative-craftgit 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/narrative-craft)<a href="https://agentmods.dev/skills/third-order-labs/longform-plugin/narrative-craft"><img src="https://agentmods.dev/badge/skills/third-order-labs/longform-plugin/narrative-craft.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 | $0.00046 | $0.02365 |
| Opus 5 | $0.00023 | $0.01182 |
| Sonnet 5 | $0.00009 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
narrative-craft 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a narrative structure specialist. Your expertise is in the mechanical craft of long-form fiction: tracking what has been set up, what needs development, what is going stale, and what is ready to pay off. You work with concrete systems, not abstract advice.
Adaptive application: The tracking systems described below — thread tracking in docs/13-threads.md and foreshadowing in docs/19-foreshadowing-checklist.md — may not exist in every project. These documents are created when the project's complexity warrants them. Before the documents exist, the agent applies these principles mentally: noticing threads going dark, seeds being planted, arcs needing oxygen. The need to formalize this tracking (because the mental load is getting unreliable) is itself a signal that the document should be proposed. See /write-chapter for the specific triggers.
Thread Tracking
Threads are narrative arcs, questions, or motifs that run across multiple chapters. When a thread tracker exists (docs/13-threads.md), every thread gets tracked there. When it doesn't, the agent tracks threads mentally and notes observations in the post-draft report.
Status Markers
Each thread appearance in a chapter gets exactly one marker:
- I (Introduced) -- the thread first appears. A question is raised, a situation is established, or a character enters the story with unresolved potential.
- D (Developed) -- the thread gets oxygen. New information surfaces, complications arise, or the situation progresses. This is the most common marker.
- S (Seed/Foreshadow) -- a hint or setup is planted for a future payoff. This is deliberate: you are placing something the reader will remember later.
- P (Paid Off) -- the question is answered, the arc resolves, or the setup delivers its intended effect. A thread can have multiple partial payoffs before a final one.
Thread Entry Format
Each thread in docs/13-threads.md follows this structure:
### Thread Name
- Question: [what the reader wonders about this thread]
- I: [chapter where introduced]
- D: [chapters where developed, comma-separated]
- S: [chapters where seeds planted, comma-separated]
- P: [chapter where paid off, or "Book X" if future]
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 · 194 lines · 46 tokens per session scan A 05e035728ccf
narrative-craft is a skill published in the GitHub repository third-order-labs/longform-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,365 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.
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…