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 lossless-group/lossless-agent-skills --skill lossless-flavored-markdowngit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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/lossless-group/lossless-agent-skills/lossless-flavored-markdown)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/lossless-flavored-markdown"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/lossless-flavored-markdown/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/lossless-group/lossless-agent-skills/lossless-flavored-markdown"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/lossless-flavored-markdown.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 | $0.00158 | $0.03072 |
| Opus 5 | $0.00079 | $0.01536 |
| Sonnet 5 | $0.00032 | $0.00614 |
| Haiku 4.5 | $0.00016 | $0.00307 |
Grade A, and why
lossless-flavored-markdown 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 11d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lossless Flavored Markdown (LFM)
MDX power without MDX's opinions. A polyglot markdown spec where user-configured syntax-triggers drive a render pipeline in a frontend framework — so plain
.mdfiles get the expressive power of MDX, without the JSX-shaped lock-in.
LFM is the Lossless Group's extended-markdown spec, implemented as the @lossless-group/lfm package. The package source lives inside the astro-knots repo today (and may graduate to its own repo later). Downstream sites and apps consume it as a dependency from JSR (jsr.io), the canonical public registry. GitHub Packages is a secondary mirror for internal use.
Canonical spec (the long form, ~4,400 lines): lossless-monorepo/astro-knots/context-v/specs/Codifying-a-Comprehensive-Extended-Markdown-Flavor-and-Shared-Package.md
The paradigm in one sentence
User configurations declare syntax-triggers. Each trigger maps a markdown pattern to a component in the consuming framework. The pipeline normalises authoring syntax to component nodes and lets the framework render them.
That's the whole shape. Everything else — the trigger map, the variant registry, the theme tokens, the polyglot syntax — is implementation of that one idea.
When to use this skill
Authoring / consuming side:
- Writing or rendering content in any Astro Knots site
- Adding
@lossless-group/lfmto a new project (pnpm dlx jsr add @lossless-group/lfm), or upgrading it - Migrating an Obsidian vault into a publishable Astro site
- Debugging callouts, hex-code citations, link previews, dialog blocks, image floats
Co-development side (the package itself):
- Working in
astro-knots/packages/lfm/(or wherever the LFM source lives at the time) - Adding a new built-in trigger to the default trigger map
- Modifying the AST normaliser, the OG fetcher, the citation resolver, the wikilink resolver
- Cutting a JSR release of
@lossless-group/lfm - Promoting LFM to its own repo (when the team decides to)
What ships with it
5 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.
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.
- 11d ago First seen · 159 lines · 158 tokens per session scan A e9c6c72149e3
lossless-flavored-markdown is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 158 tokens to every session and 3,072 once invoked, about $0.0008 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
add
Process a document (PRD, architecture doc, security requirements, etc.) into structured context. Extracts relevant information and generates appropriate SCDs.
read-aloud-edge-tts
Read text or markdown files aloud to the user using the edge-tts CLI tool. Use this when the user asks to have a file, document, or text read to them.
datasheets
Extract structured specifications from electronic component datasheet PDFs — pinouts, electrical characteristics, peripherals, topology, and features. Cache extractions per project for consumption by schematic and PCB analyzers. Primary consumer infrastructure for kicad, emc, spice, and thermal analyzers. Use this…
scholarly-publishing
Use when planning an end-to-end scholarly publishing workflow, including manuscript source-of-truth, submission assets, revision/rebuttal files, camera-ready checks, reproducible build expectations, and publication package structure.
aws-wechat-article-assets
A local library for storing business descriptions, product images, and reusable writing or design presets for WeChat articles. It organizes these materials by product so other article tools can reuse them.
document-skills
Umbrella skill for document workflows (PDF/DOCX/XLSX/PPTX). Dispatches to the most specific document skill to reduce noise and improve routing precision.