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.
npx skills add knack-run/knack-starter-pack --skill first-skill-templategit clone --depth 1 https://github.com/knack-run/knack-starter-packWrote 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.
[](https://agentmods.dev/skills/knack-run/knack-starter-pack/first-skill-template)<a href="https://agentmods.dev/skills/knack-run/knack-starter-pack/first-skill-template"><img src="https://agentmods.dev/badge/skills/knack-run/knack-starter-pack/first-skill-template.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00110 | $0.02014 |
| Opus 5 | $0.00055 | $0.01007 |
| Sonnet 5 | $0.00022 | $0.00403 |
| Haiku 4.5 | $0.00011 | $0.00201 |
Grade A, and why
first-skill-template 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Skill Template
Most first-time skill authors stare at an empty SKILL.md, fail to find the canonical structure documented anywhere, and end up writing free-form prose that Claude Code can't reliably trigger on. This skill fixes that. It produces a structured stub with every section a good skill needs (frontmatter, when-to-use phrases, input-validation rules, numbered steps, an output format, a worked-example pointer, and a don'ts list), filled with sensible defaults and clearly-marked FILL IN: slots for the parts only you can write. You walk away with a file that's already half-good, and you fill in the rest.
When to use
- "I want to write my first skill, scaffold it for me."
- "Create a SKILL.md called
weekly-reviewthat helps me write a weekly review post." - "Make me a new skill at
.claude/skills/expense-categoriser/SKILL.md." - "I've got an idea for a skill that turns a long meeting note into action items, scaffold the file."
Don't use this skill when an existing skill already covers the job (Claude Code will surface duplicates), or when what you actually need is a slash command (a one-shot prompt template, not an opinionated reusable behaviour). If in doubt: skills are for behaviours you want Claude to apply repeatedly across sessions; commands are for prompts you want to fire from a keystroke.
Inputs the skill demands (in one round-trip, not three)
Ask the user for all of these in a single grouped question. If any are missing, push back; don't proceed to scaffolding until every slot is filled.
- Skill name in kebab-case (lowercase letters, digits, and hyphens; must start with a letter; no spaces, no underscores, no capitals). Examples:
weekly-review,expense-categoriser,meeting-action-extractor. RejectWeeklyReview,weekly_review,weekly review. - One-line trigger description for the skill's frontmatter. What phrase or situation should make Claude reach for this skill? "Use when the user pastes a long meeting transcript and asks for action items" is good; "a skill for meetings" is too vague. The frontmatter description is the single most important line in the file; Claude uses it to decide whether to invoke.
- One-paragraph job-to-be-done. Three to five sentences. What does the skill actually do, end to end? "Take a long meeting transcript and extract a numbered list of action items, each with the owner, the deadline, and one sentence of context. Refuses to invent owners or deadlines that aren't in the transcript." This becomes the intro paragraph of the SKILL.md.
- Location:
.claude/skills/<name>/SKILL.md(project-local, recommended for skills tied to a specific repo) or~/.claude/skills/<name>/SKILL.md(user-global, applied across all your projects). Default to project-local if unspecified.
What ships with it
1 file 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.
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 · 89 lines · 110 tokens per session scan A d6f01899c86d
first-skill-template is a skill published in the GitHub repository knack-run/knack-starter-pack (1 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 2,014 once invoked, about $0.0006 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.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.