skill-frontmatter

skill-frontmatter is a skill for Claude Code from latestaiagents/agent-skills. It costs 98 tokens per session (1,331 once invoked), scanned A, original, MIT.

A guide to writing the YAML header at the top of a SKILL.md file. That header tells the coding agent what the skill is called and when it should be loaded.

In plain words
What is it for?
It helps create or review skill names, descriptions, and activation keywords, and troubleshoot skills that are not being loaded.
Why use it?
Correct metadata makes a skill easier for the agent to recognize; mistakes can stop it from activating.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the skills-authoring plugin — 4 skills shipped together , and of latestaiagents

Good fit It helps create or review skill names, descriptions, and activation keywords, and troubleshoot skills that are not being loaded.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/skill-frontmatter
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 latestaiagents/agent-skills --skill skill-frontmatter
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Made for: Claude Code.

Or install skills-authoring, the plugin that ships this one along with the rest of its 4 skills.

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 skill-frontmatter

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/skill-frontmatter/github.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/skill-frontmatter)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/skill-frontmatter"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/skill-frontmatter/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 skill-frontmatter

Your own site · 80×15
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/skill-frontmatter"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/skill-frontmatter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,331 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 $0.00098 $0.01331
Opus 5 $0.00049 $0.00665
Sonnet 5 $0.00020 $0.00266
Haiku 4.5 $0.00010 $0.00133

Measured 5d ago against content hash c6af78d3e7b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-frontmatter 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.

skills/skills-authoring/skill-frontmatter/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Frontmatter

The frontmatter is what the model reads to decide whether to load your skill. Get it wrong and the skill never fires.

When to Use

  • Authoring a new SKILL.md
  • Debugging "my skill isn't activating"
  • Reviewing a PR that adds a skill

Required Fields

---
name: kebab-case-name
description: |
  Sentence 1: what the skill does.
  Sentence 2: when to use it (specific trigger conditions).
  Sentence 3: activation keywords (phrases users say).
---

That's it. name and description. Nothing else is required by most clients.

The name Field

  • Kebab-casemerge-conflict-surgeon, not MergeConflictSurgeon
  • Matches directory name — directory holding the SKILL.md must have the same name
  • Verb-led or role-led:
    • Action: resolve-merge-conflict
    • Role: owasp-auditor
    • Topic: mcp-server-authoring
  • Unique across your skill set — two skills with the same name collide

The description Field

This is THE activation signal. Model reads it and matches against the user's message.

Three-sentence structure

  1. What — one sentence on the skill's purpose (action-first)
  2. When — specific trigger conditions
  3. Keywords — phrases users actually say
description: |
  Systematic merge conflict resolution with context analysis and safe resolution.
  Use this skill when the user has merge conflicts, needs help resolving conflicting changes, or is stuck on a rebase.
  Activate when: merge conflict, conflict resolution, git merge failed, rebase conflict, CONFLICT markers.

Length

  • Minimum: 2 sentences. Shorter = under-specified; misses activations
  • Sweet spot: 3-5 sentences, ~60-150 words
  • Maximum: don't exceed ~200 words; longer dilutes the signal

Voice

  • Second-person or imperative
  • Specific, not abstract: "when user is debugging a null pointer in Java" beats "helps with bugs"
  • Name the tools/frameworks — tsc, Next.js, LangGraph etc. Users and models match on these

Read the full file on GitHub · 164 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.

  1. 5d ago First seen · 164 lines · 98 tokens per session scan A c6af78d3e7b5

Subscribe to this mod's changes

skill-frontmatter is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,331 once invoked, about $0.0005 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 2026-09-03.