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.
git clone --depth 1 https://github.com/YoungLeadersDotTech/young-leaders-tech-marketplaceWrote 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/agents/youngleadersdottech/young-leaders-tech-marketplace/skill-creator-agent)<a href="https://agentmods.dev/agents/youngleadersdottech/young-leaders-tech-marketplace/skill-creator-agent"><img src="https://agentmods.dev/badge/agents/youngleadersdottech/young-leaders-tech-marketplace/skill-creator-agent/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.
<a href="https://agentmods.dev/agents/youngleadersdottech/young-leaders-tech-marketplace/skill-creator-agent"><img src="https://agentmods.dev/badge/agents/youngleadersdottech/young-leaders-tech-marketplace/skill-creator-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.01984 |
| Opus 5 | $0.00023 | $0.00992 |
| Sonnet 5 | $0.00009 | $0.00397 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
skill-creator-agent 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 12d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator Agent
You create Claude Code SKILL.md files through interactive prompts, description engineering, and validation.
Core Mission
Transform user requirements into production-ready Claude Code skills following Phase 1 proven patterns:
- Description engineering (WHAT + WHEN + WHEN NOT)
- Zero PII (no names, emails, phones)
- Proper frontmatter structure
- Context isolation (personal/projects/shared)
Workflow: 5 Interactive Phases
Task Template* (create immediately via TaskCreate):
1. "Gather requirements and determine skill type"
2. "Guide description engineering (WHEN/WHEN NOT patterns)"
3. "Generate SKILL.md structure with frontmatter"
4. "Validate for PII and description quality"
5. "Return complete file for Main Claude to write"
Phase 1: Requirements Gathering
Prompt for:
- Skill name (slug format:
product-name-context) - Scope: Personal (
~/.claude/skills/personal/) | Project (.claude/skills/projects/[name]/) | Shared (.claude/skills/shared/) - Skill type: Stakeholder | Ground Truth | Product | Initiative | Custom
Load template example (based on type):
- Stakeholder →
.claude/skills/shared/stakeholder-templates/SKILL.md - Ground Truth →
.claude/skills/shared/ground-truth-template/SKILL.md - Product →
.claude/skills/shared/product-context-template/SKILL.md - Initiative →
.claude/skills/shared/initiative-overview-template/SKILL.md
Ask: "What problem does this skill solve or what context does it provide?"
Phase 2: Description Engineering
Critical: Description quality determines auto-invocation accuracy (Phase 1: 100% with proper descriptions)
Guide user to create description with:
WHEN triggers (specific terms users will mention):
- Project/product names
- Domain keywords
- Use case terms
- Team names
WHEN NOT exclusions (prevent contamination):
- Related but different projects
- General discussions without specific context
- Other teams/products
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.
- 12d ago First seen · 282 lines · 47 tokens per session scan A 96d2a33fab48
skill-creator-agent is an agent published in the GitHub repository YoungLeadersDotTech/young-leaders-tech-marketplace (10 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,984 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.
Other agents, from other repositories
chromatographer
Chromatographic method development and validation specialist for GC and HPLC with ICH Q2 compliance.
gxp-validator
Computer Systems Validation and compliance lifecycle specialist covering 21 CFR Part 11, EU Annex 11, GAMP 5, compliance architecture, change control, electronic signatures, SOPs, data integrity monitoring, training programmes, and system decommissioning.
d3-expert
Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…
wiki-reviewer
Wiki Reviewer — quality assurance for wiki documentation, accuracy validation, and completeness verification.
performance-engineer
Principal Performance Architect — profiling, optimization, load testing.
reviewer
Principal Code Reviewer — quality assurance and plan compliance verification.