agentmods.dev

talk-html

talk-html is a skill for Claude Code from LiuShiyuMath/talk-html-plugin. It costs 0 tokens per session (17,282 once invoked), scanned B, original, no licence file.

A tool for turning a conversation or written material into a shareable HTML one-page document. HTML is the format used to build pages viewed in a web browser.

In plain words
What is it for?
Use it to make recaps, postmortems, retrospectives, status boards, handover letters, executive updates, and decision logs.
Why use it?
It creates a linkable document when a chat transcript is too long or unsuitable for sharing directly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the talk-html-plugin plugin — 3 skills, 9 commands shipped together

not rated 5repo 5mo ago B scan 0 tokens no licence

Good fit Use it to make recaps, postmortems, retrospectives, status boards, handover letters, executive updates, and decision logs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liushiyumath/talk-html-plugin/talk-html
View source ↗ LiuShiyuMath/talk-html-plugin liushiyumath.github.io
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 LiuShiyuMath/talk-html-plugin --skill talk-html
Clone the repo
git clone --depth 1 https://github.com/LiuShiyuMath/talk-html-plugin

Made for: Claude Code.

Or install talk-html-plugin, the plugin that ships this one along with the rest of its 3 skills, 9 commands.

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.

agentmods badge for talk-html

README.md
[![agentmods](https://agentmods.dev/badge/skills/liushiyumath/talk-html-plugin/talk-html/github.svg)](https://agentmods.dev/skills/liushiyumath/talk-html-plugin/talk-html)
Your own site
<a href="https://agentmods.dev/skills/liushiyumath/talk-html-plugin/talk-html"><img src="https://agentmods.dev/badge/skills/liushiyumath/talk-html-plugin/talk-html/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.

agentmods 80×15 button for talk-html

Your own site · 80×15
<a href="https://agentmods.dev/skills/liushiyumath/talk-html-plugin/talk-html"><img src="https://agentmods.dev/badge/skills/liushiyumath/talk-html-plugin/talk-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,282 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.17282
Opus 5.5 $0.00000 $0.06913
Sonnet 5.5 $0.00000 $0.03456
Haiku 4.5 $0.00000 $0.01728

Measured 2mo ago against content hash a28e44831eda, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

talk-html scanned grade B with 2 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (publish.sh, recall.sh, record-playwright.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**The upload requires no tool permission.** `publish.sh` is pre-authorized at the user level in `~/.claude/settings.json` (`permissions.allow` lists every invocation form — `bash`-prefixed and direct-exec, `~/.agents/...

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

log`, `curl`, or the generator and land on the same numbers. "Real run" in
skills/talk-html/SKILL.md · 957 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

6 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.

  1. 2mo ago First seen · 957 lines · 0 tokens per session scan B a28e44831eda

Subscribe to this mod's changes

talk-html is a skill published in the GitHub repository LiuShiyuMath/talk-html-plugin (5 stars, last pushed 5mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 17,282 tokens. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Writing and docs
Related

talk-html compared with skills from other repositories

talk-html next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
talk-htmlLiuShiyuMath/talk-html-pluginSkill55mo agononeB0Claude Code
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill316k8d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code