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 AIStoryHub/etincel --skill etincel-nonfictiongit clone --depth 1 https://github.com/AIStoryHub/etincelWrote 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/aistoryhub/etincel/etincel-nonfiction)<a href="https://agentmods.dev/skills/aistoryhub/etincel/etincel-nonfiction"><img src="https://agentmods.dev/badge/skills/aistoryhub/etincel/etincel-nonfiction/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/aistoryhub/etincel/etincel-nonfiction"><img src="https://agentmods.dev/badge/skills/aistoryhub/etincel/etincel-nonfiction.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 | $0.00136 | $0.04203 |
| Opus 5 | $0.00068 | $0.02101 |
| Sonnet 5 | $0.00027 | $0.00841 |
| Haiku 4.5 | $0.00014 | $0.00420 |
Grade A, and why
etincel-nonfiction 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Étincel Non-Fiction
This skill produces non-fiction prose that reads as if a specific person wrote it, not a model's default output, and it keeps the user in control of every change instead of silently rewriting things behind their back. It pairs with the etincel-nonfiction MCP server's tools: list_styles, get_style_guide, train_style, audit_text, set_default_style, the dictionary tools add_banned_word, remove_banned_word, add_custom_word, remove_custom_word, list_dictionary, and the instructions tools set_style_instructions, clear_style_instructions, get_style_instructions.
When to use this skill
Any non-fiction prose request of meaningful length: email, essay, blog post, newsletter, memo, op-ed, LinkedIn long-form, talk script, README intro, PR description, docs section. Also shorter pieces (an opening line, a closing paragraph) when the user signals they care about voice or tone.
Do not use it for: code, structured data, slide bullets, raw outlines, transcripts, or terse status updates. Those aren't prose.
This skill assists whatever the user is already writing in. It does not send emails, publish posts, or manage documents itself; the user (or another tool) still owns sending, publishing, and saving. This skill only shapes text.
Step 0: pick a style
Before drafting or revising, determine which voice to write in, in this order:
- If the user names a style or voice in the request, use that.
- Otherwise call
get_style_guidewith the id fromset_default_style, if one exists (calllist_stylesto check). - Otherwise call
list_styles, show the user the options (presets and any trained voices), and ask which to use, unless the request is low-stakes (a quick email reply), in which case default to thedirect-warmpreset and mention which one you used.
If the user wants a style trained from their own writing and hasn't trained one yet, offer train_style: they supply a few real samples (a few paragraphs each, more samples is better), and it persists a voice profile from measured habits (sentence rhythm, contraction rate, em-dash use, paragraph variance, recurring phrasing), not a vibes-based impression.
What ships with it
1 file 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.
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.
- 12d ago First seen · 182 lines · 0 tokens per session scan A 16605f8e2cf5
etincel-nonfiction is a skill published in the GitHub repository AIStoryHub/etincel (8 stars, last pushed 28d ago), licensed MIT. It adds 136 tokens to every session and 4,203 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 2026-08-31.
Other skills, from other repositories
ai-tells-review
Use when public prose still sounds machine-written after ai-tells-scan. Complements ai-tells-scan's mechanical pass with structural judgment: rhythm, hedging, rhetorical reflexes, and performative emphasis. Trigger on 'review for AI tells,' 'does this read AI,' 'strip the AI smell,' or 'make this less AI.'.
ai-tells-scan
Use when writing tasks produce prose artifacts (READMEs, docs, PR text, tutorials, guides, posts, release notes) and need a fast surface scan for AI tells. Auto-engages on prose writing tasks; checks banned punctuation, stock vocabulary, and mechanical patterns. For the structural judgment pass on rhythm and…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
omh-rust
This is a Hermes-native rust workflow skill.
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.