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 agentmods add skills/smk-labs/claude-plugins/reportnpx skills add smk-labs/claude-plugins --skill reportgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/report)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/report"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/report.svg" alt="Measured on agentmods" 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 | $0.00129 | $0.03904 |
| Opus 5 | $0.00064 | $0.01952 |
| Sonnet 5 | $0.00026 | $0.00781 |
| Haiku 4.5 | $0.00013 | $0.00390 |
Grade A, and why
report 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
report: the chat card, as a standalone HTML file
One goal: the saved report looks EXACTLY like the chat cards. You never design, never write CSS; a script injects the kit.
Workflow
- Collect content. If the user is exporting an existing card, reuse that card's CONTENT HTML verbatim, then apply only the changes they asked for (extend, add sections, more detail). Otherwise write fresh content. Building blocks only, no
<style>, no<script>, no wrapper div:<h2>once as title,<p class="lead">,<h3>sections,<p>,<ul>/<ol>,<li class="ok|no">, callouts<div class="cal tip|note|warn|danger"><div>…</div></div>,<code>around every LTR token,<table>+<span class="badge ok|warn|info">(10+ row stat tables:<table class="zebra dense">, striped + tight, combinable; 100+ rows: wrap as<div class="scroll-table"><table>...</table></div>for a scrollbox with pinned header that expands fully in print; very wide tables:<div class="scroll-table wide">keeps cells on one line and scrolls sideways, wraps again in print), kv,grid/kpi/trend(+ optional compact caveat<div class="f">last inside a kpi),bars(+ two-metric total/subset overlay<div class="bar duo">with two<i>in the track, first total second subset, both colors named once in a<div class="leg">first inside.bars:<span class="a"><i></i>total</span><span class="b"><i></i>subset</span>),spark(trend sparkline, same SVG contract as chat cards),donut,flow,tl,hub(one centre, up to eight arrowed legs;<div class="hub"><div class="c">centre<span>note</span></div><div class="s">item</div><div class="s out">item</div></div>, whereoutturns one leg's arrow around to separate "reads from" from "writes to"),hub tree(same markup plustree: a root, branches and leaves, no arrows, for items that group; a branch may nest its own<div class="s">children, and this is what nine or more items want instead of a hub),<hr>, andfold— a collapsible block<details class="fold"><summary>label</summary>…blocks…</details>, closed by default, native and JS-free, for long content the reader wants on demand (a full run log, a raw payload, a long quote); never a substitute for sections or tables. Its content is normal blocks, one level of nesting is fine, a<pre>inside wraps and scrolls vertically instead of stretching the page, and every fold prints open. Also:cards— a row of repeatable units,<div class="cards"><div class="card">…</div>…</div>, each with a free-form body (prose, a list, akv, abadge); addc2to the wrapper for exactly two per row, which is what a four-option comparison wants (2x2, no orphan card), and mark the recommended one<div class="card pick">.boxis one full-width card for a standout block, with an optional<div class="lbl">eyebrow label above its heading.cols—<div class="cols">with 2-3 child<div>s side by side for pros vs cons or before vs after.<blockquote>for a real citation, with an optional<cite>line.<div class="src">for a small caption directly under a table or chart ("source: …", "not measured").<i class="ic NAME"></i>for a minimal icon in the brand accent, sized from the surrounding text (in anh3it replaces the section dot, all-or-none across the report's headings); NAME is one of: check x alert info clock user file folder code terminal git db zap shield search link.<a class="preview" href="…"><b>title</b><span>one line of context</span><small>host</small></a>for a link to ANOTHER DOCUMENT, drawn as a document instead of akvrow — see Links out below.<figure><img src="shot.png" alt="..."><figcaption>caption</figcaption></figure>for a screenshot, diagram, or a/figanimation — read Images: when, and when not below before adding one.numbered— see below. All of these reflow or stack on narrow widths and print without wasting ink. ALL components are always available here (the script embeds the full kit), so unlike chat cards there are no snippets to manage. Skip CTA buttons:sendPromptdoes not exist in a standalone file. - Write the fragment to a temp file (scratchpad), e.g.
content.html. - Build:
- Persian:
python3 "<this skill dir>/build.py" content.html -o <target>.html - English: add
--lang en(LTR + Inter automatically) --title "..."optional; defaults to the<h2>text. Default output name if the user gave none:report-<short-slug>.htmlin the project directory (or the path they named).
- Persian:
- Deliver: the script prints the absolute path; report it as a clickable link. Offer to open it in the browser. Do not paste the HTML into chat.
What ships with it
3 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.
- 5d ago First seen · 115 lines · 129 tokens per session scan A 7ef8f54124ac
report is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It adds 129 tokens to every session and 3,904 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
summarize-meeting
Summarize a meeting transcript into structured notes with date, participants, topic, key decisions, summary points, and action items. Use when processing meeting recordings, creating meeting notes, writing meeting minutes, or recapping discussions.
reflect-solution
Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool calls or debugging detours. Defaults to the current in-context session; optionally accepts a session ID or JSONL path.…
researcher
Use when asked to create research documents, generate PDFs, make one-pagers, or create cheatsheets. Triggers: "research document", "generate PDF", "one-pager", "cheatsheet", "distinctive design". Provides HTML/Markdown/PDF with Terminal, Editorial, Corporate, Industrial, Fresh aesthetic presets.
generating-writeup
Generates academic/technical writeups with IEEE citations and pandoc PDF output. Use when creating research papers, technical reports, or documentation with references.
generate-doc-template
Generates on-brand document and deck templates — letterhead, slide, and one-pager — as SVG from the active brand profile, with editable title, subtitle, and body zones. Vector output needs no account, key, or network. Use when a user asks for a letterhead, a slide or deck master, or a branded one-pager. Trigger with…
generate-resume
Render a JSON Resume file through an HTML template into a self-contained, ATS-friendly document ready for the browser's Save-as-PDF. Use when the user asks to render, build, generate, or export their résumé/CV.