Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/antonio0720/writing-intelligencenpx agentmods add skills/antonio0720/writing-intelligence/storyWrote 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/antonio0720/writing-intelligence/story)<a href="https://agentmods.dev/skills/antonio0720/writing-intelligence/story"><img src="https://agentmods.dev/badge/skills/antonio0720/writing-intelligence/story/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/antonio0720/writing-intelligence/story"><img src="https://agentmods.dev/badge/skills/antonio0720/writing-intelligence/story.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00200 | $0.01657 |
| Opus 5.5 | $0.00080 | $0.00663 |
| Sonnet 5.5 | $0.00040 | $0.00331 |
| Haiku 4.5 | $0.00020 | $0.00166 |
Grade A, and why
writing-intelligence-story 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Intelligence v8 — Story Intelligence
Author: Antonio T. Smith Jr. — Founder & CEO, Density6 LLC
License: MIT
Version: 8.0.0
Companion to: writing-intelligence (the Sovereign Meaning Runtime) and writing-intelligence-craft (the craft library)
What this is
v8 brings the fiction half of Writing Intelligence up to the standard v4–v7 built for evidence. Four engines, each built and tested on its own, folded into one release:
| Engine | Requirements | Run it | Read first |
|---|---|---|---|
| Fiction & Thriller Intelligence | FI-01–FI-60 (B001–B060) | python3 scripts/wi-fiction.py |
references/v8/FICTION_INTELLIGENCE_CONSTITUTION.md |
| Arc, Want/Need & Ending Intelligence | N061–N120 | python3 scripts/wi-arc.py |
references/v8/ARC_ENDING_CONSTITUTION.md, ENDING_ALGEBRA.md |
| The Craft — openings, action, opposition, suspense, sequences | C121–C180 | python3 extensions/wi8/craft03/scripts/wi-craft.py |
extensions/wi8/craft03/references/v8/CRAFT03_CONSTITUTION.md |
| Japan Story OS | JP-181–JP-340 | python3 extensions/wi8/japan04/cli/wi8_japan.py |
extensions/wi8/japan04/README.md |
340 numbered requirements. Each has a stable ID, a canonical owner, an acceptance condition and an honest implementation state — many are editorial judgments that no code may claim to settle, and the registers say which.
The v8 rule
A structural pass is not a good novel. Four states are kept apart and never coerced into one another:
- Mechanical consistency — typed references resolve, events do not cause themselves, a power is used inside its stated limits and pays its stated cost, a fight's resources add up. Code can prove this.
- Interpretive signal — a claimed change with no witnessed choice, a clue nobody could have found, a promise with no payoff. Code can raise this; a person decides.
- Editorial judgment — whether the scene works. A human editor decides, and the decision is recorded as theirs.
- Reader reception — whether readers were satisfied, frightened, moved. Only an independent reader study answers it.
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 · 84 lines · 200 tokens per session scan A 6859dee77960
writing-intelligence-story is a skill published in the GitHub repository antonio0720/writing-intelligence (13 stars, last pushed yesterday), licensed MIT. It adds 200 tokens to every session and 1,657 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-25.
Other skills, from other repositories
novel-original-writing
A Chinese-language workflow for turning an original story idea directly into a filmable script, without adapting a novel or other existing source. It develops the idea through seven stages, from concept and world-building to characters, structure, performance, and aftermath.
novel-to-screen-adaptation
A process for turning a novel into a screenplay by breaking it down into its main idea, story engine, objects, scenes, episodes, and script in that order. It is an adaptation workflow, not a general script-writing tool.
video-prompt-adapter
A Chinese-language system for creating performance-focused prompts for video generation, combining acting direction, platform details, and production handoffs.
novel-review
A Chinese-language review method for diagnosing novels through characters, fate, structure, endings, and writing style. It cites supporting theory and assigns a literary score.
skill-e2e-test
A test process for checking a coding-agent skill from start to finish. The agent runs the skill's defined procedure and compares each stage with its required rules, then produces a report.
skill-evolution
A review and learning tool that extracts user preferences, corrections, and agreements from a conversation. It creates a style profile and suggests improvements to related skills.