What is agent-html-skills CLAUDE.md?

A set of project instructions for maintaining Claude Code conventions and release versions in an agent-skills repository. It covers version fields, release notes, checks, and Git tags.

It is for updating the plugin version, synchronizing versions across skill files, checking CI requirements, maintaining the changelog, and tagging releases after they reach the main branch.

It prevents code and skill versions from drifting apart and helps ensure that changes are released with the expected version and changelog updates. A Git tag is a named marker for a specific code release.

How f-labs-io/agent-html-skills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to f-labs-io/agent-html-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/f-labs-io/agent-html-skills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/f-labs-io/agent-html-skills

Made for: Claude Code.

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/instructions/f-labs-io/agent-html-skills/claude-md/github.svg)](https://agentmods.dev/instructions/f-labs-io/agent-html-skills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/f-labs-io/agent-html-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/f-labs-io/agent-html-skills/claude-md/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/instructions/f-labs-io/agent-html-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/f-labs-io/agent-html-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 901 This file is loaded in full into every session.

When invoked 901 The same file — it is already loaded in full.

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	$0.00901	$0.00901
Opus 5.5	$0.00360	$0.00360
Sonnet 5.5	$0.00180	$0.00180
Haiku 4.5	$0.00090	$0.00090

Measured 2mo ago against content hash 65a46437bb9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-html-skills CLAUDE.md 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 2mo 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-html-skills — conventions for Claude Code

Versioning (required)

Always bump the plugin version on every update — never ship changed code under the same version string.

The version lives in plugins/html-skills/.claude-plugin/plugin.json → "version".
Every skill's SKILL.md frontmatter carries the same version in metadata.version (ecosystem sites read individual skills, so per-skill versions must match the plugin version). Don't edit the 19 files by hand — run python3 scripts/sync-skills.py --set X.Y.Z to bump plugin.json and stamp every skill in one step (or --write to re-sync after a manual plugin.json bump). The script has no third-party dependencies.
Bump the minor (x.Y.0) for new skills or any behaviour/instruction change; bump the patch (x.y.Z) for small fixes (typos, tiny tweaks). Never reuse a released version.
Update plugins/html-skills/CHANGELOG.md in the same change.
After the release merges to main, tag it: git tag vX.Y.Z && git push origin vX.Y.Z (matches the existing v1.0.0 tag convention).
This bump is also load-bearing for skills.sh: it re-audits a skill only when the version string changes, so bumping is what refreshes the security badges.
Do not confuse this with the submit-payload version: 1 inside the interactive skills' SKILL.md / submit-handler.js — that is the JSON envelope schema version and is unrelated to the plugin release version.

Shared skill sections (single-sourced)

Every content skill repeats the same ## Pre-flight, ## HTML output foundation, and (interactive skills only) ## Submit pipeline sections verbatim, because skills load independently and skills.sh reads one SKILL.md at a time. Don't edit those copies:

The templates live in plugins/html-skills/assets/blocks/{preflight,foundation,submit}.md.
Each copy sits between  …  markers.
Edit the template, then run python3 scripts/sync-skills.py --write to push it into every skill. --check (run by CI) fails on any drift, on an unbraced $CLAUDE_PLUGIN_ROOT, on a name that doesn't match the skill directory, on a description over 1,024 characters (skills.sh limit), or on description + when_to_use over 1,536 characters (Claude Code truncates the pair in the skill listing).

Read the full file on GitHub · 60 lines

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.

2mo ago Changed · +34 lines · +497 tokens per session 65a46437bb9f
2mo ago First seen · 26 lines · 404 tokens per session scan A 5a7714f8862c

Subscribe to this mod's changes

agent-html-skills CLAUDE.md is an instructions file published in the GitHub repository f-labs-io/agent-html-skills (68 stars, last pushed 1mo ago), licensed MIT. It adds 901 tokens to every session, about $0.0036 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 2026-08-30.

agent-html-skills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-html-skills CLAUDE.mdf-labs-io/agent-html-skills	Instructions file	68	1mo ago	MIT	A	901	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-html-skills: Instructions file for Claude Code