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 podlite/podlite-skills --skill podlite-markupgit clone --depth 1 https://github.com/podlite/podlite-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/podlite/podlite-skills/podlite-markup)<a href="https://agentmods.dev/skills/podlite/podlite-skills/podlite-markup"><img src="https://agentmods.dev/badge/skills/podlite/podlite-skills/podlite-markup/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/podlite/podlite-skills/podlite-markup"><img src="https://agentmods.dev/badge/skills/podlite/podlite-skills/podlite-markup.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 | $0.00047 | $0.03204 |
| Opus 5 | $0.00023 | $0.01602 |
| Sonnet 5 | $0.00009 | $0.00641 |
| Haiku 4.5 | $0.00005 | $0.00320 |
Grade A, and why
podlite-markup 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 9d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Podlite Markup
Podlite is a lightweight markup language for documentation, knowledge bases, and structured content. It extends Markdown concepts with explicit block boundaries, typed attributes, and rich inline formatting.
- Extension:
.podlite - Document root:
=begin pod ... =end pod - Every directive starts with
=as first non-whitespace on its line - Full specification: https://podlite.org/specification
Block forms
Every block type supports three equivalent forms:
=head1 Title abbreviated (one line)
=for head1 :attr<val> paragraph (content until blank line)
Title text
=begin head1 :attr<val> delimited (explicit =end)
Title text
=end head1
Block types
| Block | Purpose | Example |
|---|---|---|
=head1..=head4 |
Headings | =head1 Introduction |
=para |
Explicit paragraph | =begin para :tags<ai> |
=item |
List item (=item = =item1) |
=item First point |
=item1/=item2/=item3 |
Nested lists (no level skip) | =item2 Sub-point |
=code |
Code block (verbatim) | =begin code :lang<js> |
=table |
Data table | =begin table :caption('Title') |
=data-table |
Render CSV/TSV (inline, :src<file:…>, or :src<data:…>) |
=for data-table :src<file:./planets.csv> |
=comment |
Not rendered | =begin comment |
=nested |
Indented/nested content | =begin nested :notify<warning> |
=picture |
Image | =picture diagram.png |
=defn |
Definition | =defn Term |
=toc |
Table of contents | =toc head1, head2 |
=include |
Include external content (directive) | =include file:./other.podlite |
=boundary |
Structural section divider (chapters/parts) | =boundary :caption('End of Part I') |
=formula |
Math formula | =begin formula |
=input/=output |
Pre-formatted I/O | =begin input |
Semantic blocks (UPPERCASE): =TITLE, =DESCRIPTION, =AUTHOR, =VERSION, =CHANGES, =TODO
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.
- 9d ago First seen · 322 lines · 47 tokens per session scan A eb1477fbe07e
podlite-markup is a skill published in the GitHub repository podlite/podlite-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 3,204 once invoked, about $0.0002 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
wgm
Autonomous build skill that turns a rough request into working software through a relentless requirements interview (grill), a persistent plan, and a Ralph-style build loop (analyze → implement → validate → review → record). Use when the user runs /wgm, or asks to build, implement, prototype, or ship a feature or app…
rugged
Companion review skill that stress-tests a request, spec, plan, diff, or system against the operators and environment that will actually run it, not an idealized one. Runs a disciplined lifecycle (Triage -> Context -> Bottleneck decomposition -> Simplify -> Field test -> Verdict) and emits exactly one of three…
teach-me
Companion learning skill that makes a codebase legible fast. Surveys a repository, builds a cited map, runs a guided tour in dependency order, and finishes with a validated first change so the learner has actually moved the code. Use when the user runs /teach-me, or asks to learn, understand, onboard onto, get up to…
quiz-me
Companion assessment skill that grills a user on a codebase until their understanding is proven rather than assumed. Asks one question at a time, grades every answer against the real code with citations, scores 0-100 by difficulty tier, and drills the weak areas it finds. Use when the user runs /quiz-me, or asks to be…
core-web-vitals
Audits HTML patterns that affect Core Web Vitals (LCP, CLS, INP). Checks for layout shift causes, largest contentful paint blockers, and interaction responsiveness issues. Use when optimising page performance or fixing Google PageSpeed Insights warnings.
nextjs-seo-audit
Comprehensive SEO audit skill for Next.js and HTML pages. Covers on-page optimisation, JSON-LD schema validation, meta tags, Open Graph, semantic HTML, site speed, mobile responsiveness, and backlink analysis. Use when a user asks to audit, optimise, or fix SEO issues on a webpage or website.