garnish

garnish is a skill for Claude Code from escoffier-labs/skillet. It costs 48 tokens per session (1,145 once invoked), scanned A, original, MIT.

A website metadata audit and repair process for how pages appear in search engines and social previews.

In plain words
What is it for?
Use it to audit or fix discoverability metadata before publication, following the repository’s existing framework and site policies.
Why use it?
It finds problems around the page content, such as titles, descriptions, canonical URLs, indexing rules, previews, structured data, and sitemaps.

Skill for Claude Code

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

Part of the skillet plugin — 39 skills, 1 hook shipped together

Good fit Use it to audit or fix discoverability metadata before publication, following the repository’s existing framework and site policies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/escoffier-labs/skillet/garnish
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 escoffier-labs/skillet --skill garnish
Clone the repo
git clone --depth 1 https://github.com/escoffier-labs/skillet

Made for: Claude Code.

Or install skillet, the plugin that ships this one along with the rest of its 39 skills, 1 hook.

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 garnish

README.md
[![agentmods](https://agentmods.dev/badge/skills/escoffier-labs/skillet/garnish/github.svg)](https://agentmods.dev/skills/escoffier-labs/skillet/garnish)
Your own site
<a href="https://agentmods.dev/skills/escoffier-labs/skillet/garnish"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/garnish/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 garnish

Your own site · 80×15
<a href="https://agentmods.dev/skills/escoffier-labs/skillet/garnish"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/garnish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,145 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01145
Opus 5 $0.00024 $0.00573
Sonnet 5 $0.00010 $0.00229
Haiku 4.5 $0.00005 $0.00114

Measured 10d ago against content hash 82b635dedf88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

garnish 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 10d 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.

skillet/skills/garnish/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

garnish

Garnish checks the metadata and indexing controls that surround a site's actual content. It works with the framework and policy already present in the target repository. It does not carry domains, account names, brand values, or fleet conventions from one site into another.

Choose the mode

  • AUDIT is read-only. Use it when the user asks what is wrong, whether a site is ready, or why a page is not appearing correctly in search or social previews.
  • FIX applies an accepted audit backlog, or a narrowly requested metadata change. Use the site's existing components and conventions before adding anything.

If the request says only "audit", stop after the report. Never turn an indexing review into an unrequested production change.

Read project policy first

Before checking tags, find the site's declared policy and public identity:

  • framework configuration and deployment configuration
  • the shared layout or head component
  • repository instructions, docs, or an SEO reference file
  • the production site URL and canonical path policy
  • robots, sitemap, and preview-environment rules

Project policy wins over generic advice. If the repository does not declare a production domain or indexing policy, report that gap and stop before inventing one.

AUDIT

Walk five stations. Score each 0-5, where 5 is correct and verified, 3 works with material gaps, 1 is mostly absent, and 0 actively blocks discovery.

# Station What to verify
1 Page identity One useful title and description per indexable page, one canonical URL, declared language, and no duplicate head tags
2 Social metadata Open Graph type, title, description, URL, image, and image alt text; platform-specific tags only when project policy requires them
3 Indexing policy Production robots directives match intent; previews and private environments are not indexed; robots.txt does not contradict page metadata
4 URL inventory Sitemap exists when the site needs one; sitemap URLs, canonical URLs, redirects, and trailing-slash policy agree
5 Structured and rendered output Structured data matches visible content and parses; a production build renders the expected tags without duplicates

Read the full file on GitHub · 110 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.

  1. 10d ago First seen · 110 lines · 48 tokens per session scan A 82b635dedf88

Subscribe to this mod's changes

garnish is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 1,145 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.

Related

Other skills, from other repositories

assess-interview-candidate

A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.

dongshuyan/compass-skills · 129 tokens

task-clarifier

Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…

dongshuyan/compass-skills · 74 tokens

user-profile-keeper

Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…

dongshuyan/compass-skills · 129 tokens

run-history-skill-builder

Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…

dongshuyan/compass-skills · 95 tokens

run-history-skill-upgrader

Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…

dongshuyan/compass-skills · 91 tokens

session-handoff-prompt

Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…

dongshuyan/compass-skills · 89 tokens