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 skills add xg-gh-25/SwarmAI --skill s_narrative-writinggit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_narrative-writing)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_narrative-writing"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_narrative-writing/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/xg-gh-25/swarmai/s_narrative-writing"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_narrative-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00148 | $0.00337 |
| Opus 5 | $0.00074 | $0.00169 |
| Sonnet 5 | $0.00030 | $0.00067 |
| Haiku 4.5 | $0.00015 | $0.00034 |
Grade A, and why
narrative-writing 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 8d 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.
What it actually says
Narrative Writing
This skill loads full instructions on activation. Read INSTRUCTIONS.md before proceeding.
TRIGGER: "six-pager", "PR/FAQ", "working backwards", "write a narrative", "technical doc", "HLD", "LLD", "ADR", "high-level design", "low-level design", "decision record", "SOP", "runbook", "project plan" DO NOT USE: for casual notes or quick summaries (just write directly)
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- INSTRUCTIONS.md 29 KB
- manifest.yaml 467 B
- reference/data-presentation.md 12 KB
- reference/templates/adr.md 2.8 KB
- reference/templates/hld.md 3.8 KB
- reference/templates/lld.md 3.1 KB
- reference/templates/prfaq.md 2.9 KB
- reference/templates/project-plan.md 2.9 KB
- reference/templates/six-pager.md 3.3 KB
- reference/templates/sop.md 3.0 KB
- reference/visual-formatting.md 14 KB
- reference/weasel-words.md 5.0 KB
- scripts/check-weasel-words.sh 4.9 KB runs code
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.
- 8d ago Changed · +3 lines · +90 tokens per session f386ee05a460
- 12d ago First seen · 19 lines · 58 tokens per session scan A 32d4076442ae
narrative-writing is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 337 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
patent-application
A patent-application document workflow that turns supplied invention materials into claims, a description, an abstract, and black-and-white drawings. It can also produce Markdown and Word files.
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
pdf-reader
Extract text from PDF files. Use when reading, parsing, or analyzing PDFs.
agent-sop-author
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.