A ready-made, no-build web viewer for a folder or set of Markdown documents. It provides navigation, search, themes, code highlighting, copying, raw-source viewing, and links between documents.

Use it to publish specs, architecture notes, ADRs, or other Markdown files as a small browser-based viewer. It can be configured for one self-contained HTML file or for an editable folder of files.

It lets people browse specification or documentation files in a readable interface without setting up a build system. It also keeps document navigation and reading position in one place.

specular — Skill for Claude Code and Codex by definite-d/agent-skills

Install

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.

Any agent

npx skills add definite-d/agent-skills --skill specular

Clone the repo

git clone --depth 1 https://github.com/definite-d/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/definite-d/agent-skills/specular/github.svg)](https://agentmods.dev/skills/definite-d/agent-skills/specular)

Your own site

<a href="https://agentmods.dev/skills/definite-d/agent-skills/specular"><img src="https://agentmods.dev/badge/skills/definite-d/agent-skills/specular/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/definite-d/agent-skills/specular"><img src="https://agentmods.dev/badge/skills/definite-d/agent-skills/specular.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,067 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00227	$0.01067
Opus 5.5	$0.00091	$0.00427
Sonnet 5.5	$0.00045	$0.00213
Haiku 4.5	$0.00023	$0.00107

Measured 6d ago against content hash 4aac3de2f8d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

specular 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 6d 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.

skills/specular/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specular

The viewer is already built and styled: references/viewer.html. Copy it, point it at the documents, add the libraries. Do not redesign it.

1. Ask one question

One file or folder?

One file (default). A single HTML with marked, marked-highlight, highlight.js, and the font inlined. About 640KB, mostly the font.
Folder. index.html, style.css, app.js, and vendor/ for people who want to inspect or edit the parts.

Both come from the same file.

2. Edit four things

<title> and <span class="brand">.
SPECS and PROMPTS: one { num, name, file } per document, paths relative to the viewer root. The same order drives the sidebar and the previous/next links at the end of each document.
Optional: the color tokens in :root and .light.
Optional: the sidebar group labels in the markup.

3. Libraries

The app script expects three UMD builds loaded before it: marked 12 (window.marked.marked), marked-highlight 2.1 (window.markedHighlight.markedHighlight), and the highlight.js 11 common build (global hljs). Inter 4 variable is the webfont the CSS points at, ./vendor/fonts/InterVariable.woff2. Later versions work if they keep those globals.

One file: inline the three scripts where the  marker sits, embed the font as base64, and drop the preload link. Folder: copy the files to vendor/ and vendor/fonts/, link them at the marker in the same order, and move the <style> block to style.css and the app script to app.js.

4. Serve

Any static server works, for example python3 -m http.server 8000. There are no module imports, and the viewer fetches with cache: "no-cache", so revalidation is covered. Opening the file from file:// will not load documents.

Traps

The viewer already handles these. If you rewrite one, keep the reason.

Sidebar collapse: animate width on the aside and keep the grid at auto 1fr. display: none on a grid child auto-places the reader into the empty column.
Theme flash: set the class from an inline <head> script, before the stylesheet. Doing it on load flashes.
Code colors: keep the --code-* palette. Third-party hljs themes are tuned to another background and look faded here. Every token clears 4.5:1 against --code-bg.
Highlighting: the common build only, langPrefix: "hljs language-", no highlightAuto(). Unlabeled fences stay plain on purpose.
Markdown in markdown: four backticks around the outer block, labelled markdown. CommonMark closes at the first fence of equal length, so three backticks truncate silently.
Scroll: restore only on the initial load from sessionStorage, clear it on navigation, and null the current file before swapping innerHTML.
Stale documents: fetch with cache: "no-cache". Servers send Last-Modified without Cache-Control, so browsers otherwise serve an hour-old copy.
Motion: nothing over 300ms, and respect prefers-reduced-motion.

Read the full file on GitHub · 84 lines

Files

What ships with it

2 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.

Changes

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.

6d ago First seen · 84 lines · 227 tokens per session scan A 4aac3de2f8d5

Subscribe to this mod's changes

specular is a skill published in the GitHub repository definite-d/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 227 tokens to every session and 1,067 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-29.

Documents Frontend

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

apify-youtube-transcript-scraper

Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.

sickn33/agentic-awesome-skills · 48 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens