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 jiahuiqu17/paper-signal --skill paper-signal-seriesgit clone --depth 1 https://github.com/jiahuiqu17/paper-signalWrote 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/jiahuiqu17/paper-signal/paper-signal-series)<a href="https://agentmods.dev/skills/jiahuiqu17/paper-signal/paper-signal-series"><img src="https://agentmods.dev/badge/skills/jiahuiqu17/paper-signal/paper-signal-series/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/jiahuiqu17/paper-signal/paper-signal-series"><img src="https://agentmods.dev/badge/skills/jiahuiqu17/paper-signal/paper-signal-series.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 | $0.00124 | $0.01083 |
| Opus 5 | $0.00062 | $0.00541 |
| Sonnet 5 | $0.00025 | $0.00217 |
| Haiku 4.5 | $0.00012 | $0.00108 |
Grade A, and why
paper-signal-series 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Signal Series
Turn content into a sequence with one editorial promise and several visually distinct images. Shared material creates continuity; each card's subject controls its composition.
Load the shared system
Read these companion files from ../paper-signal/:
references/core-workflow.mdreferences/subject-routing.mdreferences/visual-language.mdreferences/content-architecture.mdreferences/presets.mdreferences/prompt-compiler.mdreferences/quality-contract.md
Read references/evidence-ledger.md for factual claims and references/human-voice.md for personal-sharing or recommendation copy.
Workflow
1. Resolve the post promise
Write one sentence describing what the viewer will feel, understand, or decide after the final swipe. Split unrelated outcomes into separate posts.
Extract platform, audience, source material, language, image count, visible text, supplied photos, exact facts, caption need, public-source-label policy, and output destination.
2. Choose the sequence strategy
Select one:
story-led— atmosphere or experience opens the sequence; reveal context gradually.value-led— conclusion first; follow with useful evidence, tradeoffs, and fit.visual-led— hero image first; alternate context, detail, object, person, and pause.
Recommend one strategy and count. Default to 4-6 images for ordinary social posts and three substantial items when each needs facts, tradeoffs, and fit.
3. Build the content architecture
Create:
analysis.md— promise, audience tension, source/evidence map, scope, and visual opportunitiesoutline.md— one job, takeaway, exact on-image text, subject route, composition mode, caption handoff, and swipe reason per imagecaption.md— natural publishable copy when requestedevidence.json— only when facts, reviews, rankings, numbers, or source documents are involved
Keep one dominant idea per image. Move nuance to the caption.
4. Route every image independently
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 · 105 lines · 124 tokens per session scan A f710342fec42
paper-signal-series is a skill published in the GitHub repository jiahuiqu17/paper-signal (109 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 1,083 once invoked, about $0.0006 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
poster-generator
Generates professional designer-grade posters, flyers, campaign visuals, event posters, and product posters. Use when the user asks for 海报, poster, flyer, campaign visual, event poster, product poster, promotional visual, or high-end marketing key visual.
ppt-image-share-builder
Build image2-first classroom PPT page images from a topic, source files, reference PPT style, and iterative user feedback. Use when Codex needs to create image2-ready per-page prompts, generate polished PPT page images, QA a contact sheet, insert the final images into a PPTX wrapper, and write a timed presentation…
craft-diorama-still-life
A skill for turning an article, opinion, or product claim into a handcrafted object-metaphor still-life prompt.
cyber-terminal-schematic
A skill for turning a topic, technical idea, agent workflow, or data finding into a cyber-terminal-style image prompt.
ink-satire-figures
A prompt-writing guide for black-and-white satirical drawings inspired by traditional Chinese picture stories, using simple ink lines, side-view figures, and everyday scenes.
duotone-press-collage
A prompt-writing guide for collage images that look like two-color printed cutouts, with halftone objects, white cut edges, registration marks, crop marks, and a Chinese label.